{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T03:43:19Z","timestamp":1781408599007,"version":"3.54.1"},"reference-count":328,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20257-0","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T11:02:16Z","timestamp":1729162936000},"page":"2327-2484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A comprehensive review on performance-based comparative analysis, categorization, classification and mapping of text extraction system techniques for images"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1113-822X","authenticated-orcid":false,"given":"Deepika","family":"Ghai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sobhit","family":"Saxena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gittaly","family":"Dhingra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suman Lata","family":"Tripathi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"issue":"12","key":"20257_CR1","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1109\/TCSVT.2002.806812","volume":"12","author":"M Acharyya","year":"2002","unstructured":"Acharyya M, Kundu MK (2002) Document image segmentation using wavelet scale-space features. IEEE Trans Circuits Syst Video Technol 12(12):1117\u20131127","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"20257_CR2","unstructured":"Agarwal R (2022) Deep learning based OCR for text in the wild.\u00a0https:\/\/nanonets.com\/blog\/deep-learning-ocr\/. Accessed 5\u00a0Aug 2022"},{"key":"20257_CR3","doi-asserted-by":"crossref","first-page":"e717","DOI":"10.7717\/peerj-cs.717","volume":"7","author":"H Ali","year":"2021","unstructured":"Ali H, Iqbal K, Mujtaba G, Fayyaz A, Bulbul MF, Karam FW, Zahir A (2021) Urdu text in natural scene images: a new dataset and preliminary text detection. PeerJ Comput Sci 7:e717","journal-title":"PeerJ Comput Sci"},{"key":"20257_CR4","doi-asserted-by":"crossref","unstructured":"Ambai M, Yoshida Y (2011) CARD: Compact and real-time descriptors. In: 2011 International Conference on Computer Vision, IEEE, pp. 97\u2013104.","DOI":"10.1109\/ICCV.2011.6126230"},{"issue":"5","key":"20257_CR5","first-page":"229","volume":"3","author":"SA Angadi","year":"2010","unstructured":"Angadi SA, Kodabagi MM (2010) A texture based methodology for text region extraction from low resolution natural scene images. Int J Image Process 3(5):229\u2013245","journal-title":"Int J Image Process"},{"issue":"4","key":"20257_CR6","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1016\/S0031-3203(01)00086-3","volume":"35","author":"S Antani","year":"2002","unstructured":"Antani S, Kasturi R, Jain R (2002) A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video. Pattern Recogn 35(4):945\u2013965","journal-title":"Pattern Recogn"},{"issue":"9","key":"20257_CR7","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1016\/j.imavis.2010.03.004","volume":"28","author":"M Anthimopoulos","year":"2010","unstructured":"Anthimopoulos M, Gatos B, Pratikakis I (2010) A two-stage scheme for text detection in video images. Image Vis Comput 28(9):1413\u20131426","journal-title":"Image Vis Comput"},{"key":"20257_CR8","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.protcy.2012.05.035","volume":"4","author":"VM Aradhya","year":"2012","unstructured":"Aradhya VM, Pavithra MS, Naveena C (2012) A robust multilingual text detection approach based on transforms and wavelet entropy. Procedia Technol 4:232\u2013237","journal-title":"Procedia Technol"},{"issue":"3","key":"20257_CR9","first-page":"895","volume":"2","author":"K Arai","year":"2011","unstructured":"Arai K, Tolle H (2011) Text extraction from TV commercial using blob extraction method. Int J Res Rev Comput Sci 2(3):895\u2013899","journal-title":"Int J Res Rev Comput Sci"},{"issue":"4","key":"20257_CR10","first-page":"502","volume":"36","author":"S Audithan","year":"2009","unstructured":"Audithan S, Chandrasekaran RM (2009) Document text extraction from document images using Haar discrete wavelet transform. Eur J Sci Res 36(4):502\u2013512","journal-title":"Eur J Sci Res"},{"key":"20257_CR11","doi-asserted-by":"crossref","unstructured":"Azadboni MK, Behrad A (2012) Text detection and character extraction in color images using FFT domain filtering and SVM classification. In: 6th International Symposium on Telecommunications (IST) Nov 6. IEEE, pp. 794\u2013799.","DOI":"10.1109\/ISTEL.2012.6483094"},{"key":"20257_CR12","doi-asserted-by":"crossref","unstructured":"Bai B, Yin F, Liu CL (2014) A seed-based segmentation method for scene text extraction. In: 2014 11th IAPR International Workshop on Document Analysis Systems Apr 7. IEEE, pp. 262\u2013266.","DOI":"10.1109\/DAS.2014.34"},{"key":"20257_CR13","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.patcog.2016.12.005","volume":"66","author":"X Bai","year":"2017","unstructured":"Bai X, Shi B, Zhang C, Cai X, Qi L (2017) Text\/non-text image classification in the wild with convolutional neural networks. Pattern Recogn 66:437\u2013446","journal-title":"Pattern Recogn"},{"key":"20257_CR14","doi-asserted-by":"crossref","unstructured":"Bansal A, Chaudhury S, Roy SD, Srivastava JB (2014) Newspaper article extraction using hierarchical fixed point model. In: 2014 11th IAPR International Workshop on Document Analysis Systems Apr 7. IEEE, pp. 257\u2013261.","DOI":"10.1109\/DAS.2014.42"},{"issue":"5","key":"20257_CR15","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.3390\/app11052332","volume":"11","author":"S Barburiceanu","year":"2021","unstructured":"Barburiceanu S, Terebes R, Meza S (2021) 3D texture feature extraction and classification using GLCM and LBP-based descriptors. Appl Sci 11(5):2332\u20132357","journal-title":"Appl Sci"},{"key":"20257_CR16","unstructured":"Cai M, Song J, Lyu MR (2002) A new approach for video text detection. In: Proceedings of International Conference on Image Processing Sep 22, vol. 1. IEEE, p. I."},{"issue":"12","key":"20257_CR17","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.3390\/sym12121956","volume":"12","author":"D Cao","year":"2020","unstructured":"Cao D, Zhong Y, Wang L, He Y, Dang J (2020) Scene text detection in natural images: a review. Symmetry 12(12):1956","journal-title":"Symmetry"},{"key":"20257_CR18","doi-asserted-by":"crossref","first-page":"62805","DOI":"10.1109\/ACCESS.2019.2915513","volume":"7","author":"M Cao","year":"2019","unstructured":"Cao M, Zou Y, Yang D, Liu C (2019) GISCA: Gradient-inductive segmentation network with contextual attention for scene text detection. IEEE Access 7:62805\u201362816","journal-title":"IEEE Access"},{"key":"20257_CR19","doi-asserted-by":"crossref","unstructured":"Chandio AA, Pickering M, Shafi K (2018) Character classification and recognition for Urdu texts in natural scene images. In: 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) Mar 3. IEEE, pp. 1\u20136.","DOI":"10.1109\/ICOMET.2018.8346341"},{"key":"20257_CR20","doi-asserted-by":"crossref","first-page":"10062","DOI":"10.1109\/ACCESS.2022.3144844","volume":"10","author":"AA Chandio","year":"2022","unstructured":"Chandio AA, Asikuzzaman MD, Pickering MR, Leghari M (2022) Cursive text recognition in natural scene images using deep convolutional recurrent neural network. IEEE Access 10:10062\u201310078","journal-title":"IEEE Access"},{"key":"20257_CR21","doi-asserted-by":"publisher","unstructured":"Charfi M, Kherallah M, Baati AE, Alimi AM (2012) A new approach for Arabic handwritten postal addresses recognition. https:\/\/doi.org\/10.48550\/arXiv.1204.1678.","DOI":"10.48550\/arXiv.1204.1678"},{"key":"20257_CR22","doi-asserted-by":"crossref","unstructured":"Chaudhuri AR, Mandal AK, Chaudhuri BB (2002) Page layout analyser for multilingual Indian documents. In: Language Engineering Conference, 2002. Proceedings Dec 13. IEEE, pp. 24\u201332.","DOI":"10.1109\/LEC.2002.1182287"},{"key":"20257_CR23","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1007\/978-3-319-21969-1_27","volume-title":"Image and Graphics","author":"C Chen","year":"2015","unstructured":"Chen C, Wang DH, Wang H (2015) Scene character and text recognition: the state-of-the-art. Image and Graphics. Springer, Cham, pp 310\u2013320"},{"key":"20257_CR24","unstructured":"Chen D, Luettin J (2000) A survey of text detection and recognition in images and videos. IDIAP Research Report, IDIAP-RR 00-38"},{"key":"20257_CR25","unstructured":"Chen D (2003) Text detection and recognition in images and video sequences. IDIAP Research Report, IDIAP-RR 03-44"},{"key":"20257_CR26","unstructured":"Chen D, Shearer K, Bourlard H (2001) Text enhancement with asymmetric filter for video OCR. In: Proceedings 11th International Conference on Image Analysis and Processing Sep 26. IEEE, pp. 192\u2013197."},{"key":"20257_CR27","doi-asserted-by":"crossref","unstructured":"Chen J, Takagi N (2015) A homogeneous region based methodology for text extraction from natural scene images. In: 2015 International Conference on Informatics, Electronics & Vision (ICIEV) Jun 15. IEEE, pp. 1\u20136.","DOI":"10.1109\/ICIEV.2015.7334037"},{"key":"20257_CR28","doi-asserted-by":"crossref","unstructured":"Chen K, Yin F, Hussain A, Liu CL (2015) Efficient text localization in born-digital images by local contrast-based segmentation. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR) Aug 23. IEEE, pp. 291\u2013295.","DOI":"10.1109\/ICDAR.2015.7333770"},{"key":"20257_CR29","doi-asserted-by":"crossref","unstructured":"Chen K, Yin F, Liu CL (2016) Effective candidate component extraction for text localization in born-digital images by combining text contours and stroke interior regions. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS) Apr 11. IEEE, pp. 352\u2013357.","DOI":"10.1109\/DAS.2016.30"},{"key":"20257_CR30","unstructured":"Chen PY, Liao EC (2002) A new algorithm for Haar discrete wavelet transform. In: IEEE International Symposium on Intelligent Signal Processing and Communication Systems, vol. 21, no. 24, pp. 453\u2013457."},{"key":"20257_CR31","doi-asserted-by":"crossref","unstructured":"Chen Q, Song Y, Zhang Y (2017) Scene text extraction with local symmetry transform. In: 2017 15th IAPR International Conference on Machine Vision Applications (MVA) May 8. IEEE, pp. 246\u2013249.","DOI":"10.23919\/MVA.2017.7986847"},{"key":"20257_CR32","doi-asserted-by":"crossref","unstructured":"Chen T (2008) Text localization using DWT fusion algorithm. In: 2008 11th IEEE International Conference on Communication Technology Nov 10. IEEE, pp. 722\u2013725.","DOI":"10.1109\/ICCT.2008.4716220"},{"key":"20257_CR33","doi-asserted-by":"crossref","unstructured":"Chiba N, Liu X (2015) Character extraction by integrating color into edge-based methods. In: 2015 14th IAPR International Conference on Machine Vision Applications (MVA), IEEE, pp. 73\u201376.","DOI":"10.1109\/MVA.2015.7153136"},{"key":"20257_CR34","doi-asserted-by":"crossref","unstructured":"Chidiac NM, Damien P, Yaacoub C (2016) A robust algorithm for text extraction from images. In: 2016 39th International Conference on Telecommunications and Signal Processing (TSP) Jun 27. IEEE, pp. 493\u2013497.","DOI":"10.1109\/TSP.2016.7760928"},{"key":"20257_CR35","doi-asserted-by":"crossref","unstructured":"Cho J, Chang YS, Lee SH (2018) Theme-related keyword extraction from free text descriptions of image contents for tagging. In: 2018 20th International Conference on Advanced Communication Technology (ICACT) Feb 11. IEEE, pp. 537\u2013541.","DOI":"10.23919\/ICACT.2018.8323822"},{"key":"20257_CR36","doi-asserted-by":"crossref","unstructured":"Chun BT, Bae Y, Kim TY (1999) Automatic text extraction in digital videos using FFT and neural network. In: FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No. 99CH36315) Aug 22, vol. 2. IEEE, pp. 1112\u20131115.","DOI":"10.1109\/FUZZY.1999.793110"},{"key":"20257_CR37","doi-asserted-by":"crossref","unstructured":"Crandall D, Kasturi R (2001) Robust detection of stylized text events in digital video. In: Proceedings of 6th International Conference on Document Analysis and Recognition Sep 13. IEEE, pp. 865\u2013869.","DOI":"10.1109\/ICDAR.2001.953910"},{"key":"20257_CR38","first-page":"e2","volume":"3","author":"L Deng","year":"2014","unstructured":"Deng L (2014) A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Trans Signal Inf Process 3:e2","journal-title":"APSIPA Trans Signal Inf Process"},{"key":"20257_CR39","doi-asserted-by":"publisher","unstructured":"Deng L, Liu Y (eds.) (2018) Deep learning in natural language processing. Springer. https:\/\/doi.org\/10.1007\/978-981-10-5209-5","DOI":"10.1007\/978-981-10-5209-5"},{"issue":"12","key":"20257_CR40","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.1016\/S0031-3203(00)00160-6","volume":"34","author":"S Deng","year":"2001","unstructured":"Deng S, Latifi S, Regentova E (2001) Document segmentation using polynomial Spline wavelets. Pattern Recogn 34(12):2533\u20132545","journal-title":"Pattern Recogn"},{"key":"20257_CR41","doi-asserted-by":"crossref","unstructured":"Diem M, Kleber F, Sablatnig R (2011) Text classification and document layout analysis of paper fragments. In: 2011 International Conference on Document Analysis and Recognition Sep 18. IEEE, pp. 854\u2013858.","DOI":"10.1109\/ICDAR.2011.175"},{"key":"20257_CR42","doi-asserted-by":"crossref","unstructured":"Dinh TN, Park J, Lee G (2008) Low-complexity text extraction in Korean signboards for mobile applications. In: 2008 8th IEEE International Conference on Computer and Information Technology Jul 8. IEEE, pp. 333\u2013337.","DOI":"10.1109\/CIT.2008.4594697"},{"key":"20257_CR43","doi-asserted-by":"crossref","unstructured":"Doermann D (2014) Handbook of document image processing and recognition. Tombre K (ed), London, Springer.","DOI":"10.1007\/978-0-85729-859-1"},{"key":"20257_CR44","doi-asserted-by":"crossref","unstructured":"Doermann D, Liang J, Li H (2003) Progress in camera-based document image analysis. In: 7th International Conference on Document Analysis and Recognition, 2003. Proceedings Aug 6. IEEE, pp. 606\u2013616.","DOI":"10.1109\/ICDAR.2003.1227735"},{"key":"20257_CR45","doi-asserted-by":"crossref","unstructured":"Dos Santos JE, Dubuisson B, Bortolozzi F (2002) Characterizing and distinguishing text in bank cheque images. In: Proceedings. XV Brazilian Symposium on Computer Graphics and Image Processing Oct 10. IEEE, pp. 203\u2013209.","DOI":"10.1109\/SIBGRA.2002.1167144"},{"key":"20257_CR46","doi-asserted-by":"crossref","unstructured":"Dos Santos RP, Clemente GS, Ren TI, Cavalcanti GD (2009) Text line segmentation based on morphology and histogram projection. In: 2009 10th International Conference on Document Analysis and Recognition Jul 26. IEEE, pp. 651\u2013655.","DOI":"10.1109\/ICDAR.2009.183"},{"key":"20257_CR47","doi-asserted-by":"crossref","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Jun 13. IEEE, pp. 2963\u20132970.","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"20257_CR48","doi-asserted-by":"crossref","unstructured":"Fragoso V, Gauglitz S, Zamora S, Kleban J, Turk M (2011) TranslatAR: a mobile augmented reality translator. In: 2011 IEEE Workshop on Applications of Computer Vision (WACV) Jan 5. IEEE, pp. 497\u2013502.","DOI":"10.1109\/WACV.2011.5711545"},{"key":"20257_CR49","doi-asserted-by":"crossref","first-page":"96424","DOI":"10.1109\/ACCESS.2019.2929819","volume":"7","author":"J Gao","year":"2019","unstructured":"Gao J, Wang Q, Yuan Y (2019) Convolutional regression network for multi-oriented text detection. IEEE Access 7:96424\u201396433","journal-title":"IEEE Access"},{"key":"20257_CR50","doi-asserted-by":"crossref","first-page":"71299","DOI":"10.1109\/ACCESS.2019.2919994","volume":"7","author":"X Gao","year":"2019","unstructured":"Gao X, Han S, Luo C (2019) A detection and verification model based on SSD and encoder-decoder network for scene text detection. IEEE Access 7:71299\u201371310","journal-title":"IEEE Access"},{"key":"20257_CR51","doi-asserted-by":"crossref","unstructured":"Gargi U, Antani S, Kasturi R (1998) Indexing text events in digital video databases. In: Proceedings of 14th International Conference on Pattern Recognition (Cat. No. 98EX170) Aug 20, vol. 1. IEEE, pp. 916\u2013918.","DOI":"10.1109\/ICPR.1998.711301"},{"key":"20257_CR52","unstructured":"Gatos B, Pratikakis I, Kepene K, Perantonis SJ (2005) Text detection in indoor\/outdoor scene images. In: Proceedings of First Workshop of Camera-based Document Analysis and Recognition Aug, pp. 127\u2013132."},{"key":"20257_CR53","first-page":"285","volume":"2","author":"V Gavali","year":"2013","unstructured":"Gavali V, Bombade BR (2013) Multioriented and curved text lines extraction from documents. Int J Comput Sci Mob Comput 2:285\u2013293","journal-title":"Int J Comput Sci Mob Comput"},{"issue":"3","key":"20257_CR54","first-page":"40","volume":"84","author":"D Ghai","year":"2013","unstructured":"Ghai D, Jain N (2013) Text extraction from document images-a review. Int J Comput Appl 84(3):40\u201348","journal-title":"Int J Comput Appl"},{"issue":"5","key":"20257_CR55","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1080\/18756891.2016.1237189","volume":"9","author":"D Ghai","year":"2016","unstructured":"Ghai D, Gera D, Jain N (2016) A new approach to extract text from images based on DWT and k-means clustering. Int J Comput Intell Syst 9(5):900\u2013916","journal-title":"Int J Comput Intell Syst"},{"issue":"1","key":"20257_CR56","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s11277-019-06574-w","volume":"109","author":"D Ghai","year":"2019","unstructured":"Ghai D, Jain N (2019) Comparative analysis of multi-scale wavelet decomposition and k-means clustering based text extraction. Wireless Pers Commun 109(1):455\u2013490","journal-title":"Wireless Pers Commun"},{"key":"20257_CR57","doi-asserted-by":"publisher","unstructured":"Ghai D, Jain N (2022) Comparison of different text extraction techniques for complex color images. In: Machine learning algorithms for signal and image processing, pp 139\u2013160. https:\/\/doi.org\/10.1002\/9781119861850.ch9","DOI":"10.1002\/9781119861850.ch9"},{"key":"20257_CR58","doi-asserted-by":"crossref","unstructured":"Ghai D, Tripathi SL, Saxena S, Chanda M, Alazab M (2022) Machine learning algorithms for signal and image processing, Wiley-IEEE Press, 1st ed., pp 1\u2013512","DOI":"10.1002\/9781119861850"},{"key":"20257_CR59","doi-asserted-by":"crossref","unstructured":"Ghoshal R, Roy A, Parui SK (2012) Text extraction from scene images using statistical distributions. In: 2012 3rd International Conference on Emerging Applications of Information Technology, IEEE, pp. 187\u2013190.","DOI":"10.1109\/EAIT.2012.6407892"},{"key":"20257_CR60","doi-asserted-by":"crossref","unstructured":"Gillioz A, Casas J, Mugellini E, Abou Khaled, O (2020) Overview of the Transformer-based Models for NLP Tasks. In: 15th Conference on Computer Science and Information Systems (FedCSIS), IEEE, pp. 179\u2013183.","DOI":"10.15439\/2020F20"},{"key":"20257_CR61","doi-asserted-by":"crossref","unstructured":"Gllavata J, Ewerth R, Freisleben B (2003) A robust algorithm for text detection in images. In: 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the 2003, vol. 2. IEEE, pp. 611\u2013616.","DOI":"10.1109\/ISPA.2003.1296349"},{"key":"20257_CR62","doi-asserted-by":"crossref","unstructured":"Gllavata J, Ewerth R, Freisleben B (2004) Text detection in images based on unsupervised classification of high-frequency wavelet coefficients. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, vol. 1, IEEE, pp. 425\u2013428.","DOI":"10.1109\/ICPR.2004.1334146"},{"issue":"4","key":"20257_CR63","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10032-016-0274-2","volume":"19","author":"L Gomez","year":"2016","unstructured":"Gomez L, Karatzas D (2016) A fast hierarchical method for multi-script and arbitrary oriented scene text extraction. Int J Docum Anal Recog 19(4):335\u2013349","journal-title":"Int J Docum Anal Recog"},{"key":"20257_CR64","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio, Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, p 27. https:\/\/doi.org\/10.48550\/arXiv.1406.2661"},{"key":"20257_CR65","first-page":"918","volume-title":"Asian Conference on Computer Vision Jan 13","author":"M Grabner","year":"2006","unstructured":"Grabner M, Grabner H, Bischof H (2006) Fast approximated SIFT. Asian Conference on Computer Vision Jan 13. Springer, Berlin, Heidelberg, pp 918\u2013927"},{"key":"20257_CR66","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 2315\u20132324.","DOI":"10.1109\/CVPR.2016.254"},{"key":"20257_CR67","unstructured":"Gupta P, Vohra N, Chaudhury S, Joshi SD (2000) Wavelet based page segmentation. In: Proceedings of the ICVGIP, pp. 51\u201356."},{"key":"20257_CR68","doi-asserted-by":"crossref","unstructured":"Haritaoglu I (2001) Scene text extraction and translation for handheld devices. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 2. IEEE, pp. II.","DOI":"10.1109\/CVPR.2001.990990"},{"key":"20257_CR69","doi-asserted-by":"crossref","unstructured":"Hanif SM, Prevost L, Negri PA (2008) A cascade detector for text detection in natural scene images. In: 2008 19th International Conference on Pattern Recognition, IEEE, pp. 1\u20134.","DOI":"10.1109\/ICPR.2008.4761536"},{"key":"20257_CR70","doi-asserted-by":"crossref","unstructured":"Hanif SM, Prevost L (2009) Text detection and localization in complex scene images using constrained adaboost algorithm. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp. 1\u20135.","DOI":"10.1109\/ICDAR.2009.172"},{"key":"20257_CR71","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","volume":"2","author":"X Han","year":"2021","unstructured":"Han X, Zhang Z, Ding N, Gu Y, Liu X, Huo Y, Qiu J, Yao Y, Zhang A, Zhang L, Han W, Huang M, Jin Q, Lan Y, Liu Y, Liu Z, Lu Z, Qiu X, Song R, Tang J, Wen JR, Yuan J, Zhao WX, Zhu J (2021) Pre-trained models: Past, present and future. AI Open 2:225\u2013250","journal-title":"AI Open"},{"issue":"11","key":"20257_CR72","doi-asserted-by":"crossref","first-page":"1978","DOI":"10.1109\/83.877220","volume":"9","author":"YM Hasan","year":"2000","unstructured":"Hasan YM, Karam LJ (2000) Morphological text extraction from images. IEEE Trans Image Process 9(11):1978\u20131983","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR73","doi-asserted-by":"crossref","unstructured":"Hase H, Shinokawa T, Yoneda M, Sakai M, Maruyama H (1997) Character string extraction by multi-stage relaxation. In: Proceedings of the 4th International Conference on Document Analysis and Recognition, vol. 1. IEEE, pp. 298\u2013302.","DOI":"10.1109\/ICDAR.1997.619860"},{"issue":"7","key":"20257_CR74","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1016\/S0031-3203(00)00081-9","volume":"34","author":"H Hase","year":"2001","unstructured":"Hase H, Shinokawa T, Yoneda M, Suen CY (2001) Character string extraction from color documents. Pattern Recogn 34(7):1349\u20131365","journal-title":"Pattern Recogn"},{"key":"20257_CR75","first-page":"1","volume-title":"European Conference on Computer Vision","author":"K He","year":"2010","unstructured":"He K, Sun J, Tang X (2010) Guided image filtering. European Conference on Computer Vision. Springer, Berlin, Heidelberg, pp 1\u201314"},{"key":"20257_CR76","doi-asserted-by":"crossref","unstructured":"He P, Huang W, Qiao Y, Loy CC, Tang X (2016) Reading scene text in deep convolutional sequences. In: 30th AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v30i1.10465"},{"issue":"6","key":"20257_CR77","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1109\/TIP.2016.2547588","volume":"25","author":"T He","year":"2016","unstructured":"He T, Huang W, Qiao Y, Yao J (2016) Text-attentional convolutional neural network for scene text detection. IEEE Trans Image Process 25(6):2529\u20132541","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR78","doi-asserted-by":"publisher","unstructured":"He T, Huang W, Qiao Y, Yao J (2016b) Accurate text localization in natural image with cascaded convolutional text network. https:\/\/doi.org\/10.48550\/arXiv.1603.09423.","DOI":"10.48550\/arXiv.1603.09423"},{"issue":"11","key":"20257_CR79","doi-asserted-by":"crossref","first-page":"5406","DOI":"10.1109\/TIP.2018.2855399","volume":"27","author":"W He","year":"2018","unstructured":"He W, Zhang XY, Yin F, Liu CL (2018) Multi-oriented and multi-lingual scene text detection with direct regression. IEEE Trans Image Process 27(11):5406\u20135419","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR80","doi-asserted-by":"crossref","unstructured":"Huang W, Lin Z, Yang J, Wang J (2013) Text localization in natural images using stroke feature transform and text covariance descriptors. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1241\u20131248.","DOI":"10.1109\/ICCV.2013.157"},{"key":"20257_CR81","first-page":"497","volume-title":"European conference on computer vision","author":"W Huang","year":"2014","unstructured":"Huang W, Qiao Y, Tang X (2014) Robust scene text detection with convolution neural network induced MSER trees. European conference on computer vision. Springer, Cham, pp 497\u2013511"},{"key":"20257_CR82","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/978-3-030-51935-3_26","volume-title":"International Conference on Image and Signal Processing","author":"R Islam","year":"2020","unstructured":"Islam R, Islam MR, Talukder KH (2020) Extraction and recognition of Bangla texts from natural scene images using CNN. International Conference on Image and Signal Processing. Springer, Cham, pp 243\u2013253"},{"key":"20257_CR83","doi-asserted-by":"crossref","first-page":"122666","DOI":"10.1016\/j.eswa.2023.122666","volume":"241","author":"S Islam","year":"2023","unstructured":"Islam S, Elmekki H, Elsebai A, Bentahar J, Drawel N, Rjoub G, Pedrycz W (2023) A comprehensive survey on applications of transformers for deep learning tasks. Expert Syst Appl 241:122666","journal-title":"Expert Syst Appl"},{"key":"20257_CR84","first-page":"512","volume-title":"European Conference on Computer Vision","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Deep features for text spotting. European Conference on Computer Vision. Springer, Cham, pp 512\u2013528"},{"key":"20257_CR85","doi-asserted-by":"publisher","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014b) Synthetic data and artificial neural networks for natural scene text recognition. https:\/\/doi.org\/10.48550\/arXiv.1406.2227.","DOI":"10.48550\/arXiv.1406.2227"},{"issue":"1","key":"20257_CR86","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2016) Reading text in the wild with convolutional neural networks. Int J Comput Vision 116(1):1\u201320","journal-title":"Int J Comput Vision"},{"issue":"3","key":"20257_CR87","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/BF02626996","volume":"5","author":"AK Jain","year":"1992","unstructured":"Jain AK, Bhattacharjee S (1992) Text segmentation using Gabor filters for automatic document processing. Mach Vis Appl 5(3):169\u2013184","journal-title":"Mach Vis Appl"},{"issue":"5","key":"20257_CR88","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1016\/0031-3203(95)00131-X","volume":"29","author":"AK Jain","year":"1996","unstructured":"Jain AK, Zhong Y (1996) Page segmentation using texture analysis. Pattern Recogn 29(5):743\u2013770","journal-title":"Pattern Recogn"},{"issue":"2","key":"20257_CR89","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/34.481543","volume":"18","author":"AK Jain","year":"1996","unstructured":"Jain AK, Karu K (1996) Learning texture discrimination masks. IEEE Trans Pattern Anal Mach Intell 18(2):195\u2013205","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"20257_CR90","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1016\/S0031-3203(98)00067-3","volume":"31","author":"AK Jain","year":"1998","unstructured":"Jain AK, Yu B (1998) Automatic text location in images and video frames. Pattern Recogn 31(12):2055\u20132076","journal-title":"Pattern Recogn"},{"key":"20257_CR91","unstructured":"Jagannathan L, Jawahar CV (2005) Perspective correction methods for camera based document analysis. In: Proceedings of First International Workshop on Camera-based Document Analysis and Recognition, pp. 148\u2013154."},{"issue":"4","key":"20257_CR92","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s10032-011-0170-8","volume":"15","author":"R Jayadevan","year":"2012","unstructured":"Jayadevan R, Kolhe SR, Patil PM, Pal U (2012) Automatic processing of handwritten bank cheque images: a survey. Int J Document Anal Recognit 15(4):267\u2013296","journal-title":"Int J Document Anal Recognit"},{"key":"20257_CR93","doi-asserted-by":"crossref","unstructured":"Jeong KY, Jung K, Kim EY, Kim HJ (1999) Neural network-based text location for news video indexing. In: Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), vol. 3. IEEE, pp. 319\u2013323.","DOI":"10.1109\/ICIP.1999.817127"},{"key":"20257_CR94","doi-asserted-by":"crossref","unstructured":"Ji R, Xu P, Yao H, Zhang Z, Sun X, Liu T (2008) Directional correlation analysis of local Haar binary pattern for text detection. In: 2008 IEEE International Conference on Multimedia and Expo, IEEE, pp. 885\u2013888.","DOI":"10.1109\/ICME.2008.4607577"},{"key":"20257_CR95","doi-asserted-by":"crossref","unstructured":"Ji Z, Wang J, Su YT (2009) Text detection in video frames using hybrid features. In: 2009 International Conference on Machine Learning and Cybernetics, vol. 1. IEEE, pp. 318\u2013322.","DOI":"10.1109\/ICMLC.2009.5212547"},{"key":"20257_CR96","doi-asserted-by":"crossref","unstructured":"Jianyong S, Xiling L, Jun Z (2009) An edge-based approach for video text extraction. In: 2009 International Conference on Computer Technology and Development, vol. 2. IEEE, pp. 331\u2013335.","DOI":"10.1109\/ICCTD.2009.177"},{"issue":"9","key":"20257_CR97","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1016\/j.imavis.2008.11.012","volume":"27","author":"C Jung","year":"2009","unstructured":"Jung C, Liu Q, Kim J (2009) Accurate text localization in images based on SVM output scores. Image Vis Comput 27(9):1295\u20131301","journal-title":"Image Vis Comput"},{"issue":"1","key":"20257_CR98","doi-asserted-by":"crossref","first-page":"78","DOI":"10.4218\/etrij.11.1510.0029","volume":"33","author":"J Jung","year":"2011","unstructured":"Jung J, Lee S, Cho MS, Kim JH (2011) Touch TT: Scene text extractor using touchscreen interface. ETRI J 33(1):78\u201388","journal-title":"ETRI J"},{"issue":"5","key":"20257_CR99","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/j.patcog.2003.10.012","volume":"37","author":"K Jung","year":"2004","unstructured":"Jung K, Kim KI, Jain AK (2004) Text information extraction in images and video: a survey. Pattern Recogn 37(5):977\u2013997","journal-title":"Pattern Recogn"},{"issue":"14","key":"20257_CR100","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.1016\/S0167-8655(01)00096-4","volume":"22","author":"K Jung","year":"2001","unstructured":"Jung K (2001) Neural network-based text location in color images. Pattern Recogn Lett 22(14):1503\u20131515","journal-title":"Pattern Recogn Lett"},{"key":"20257_CR101","doi-asserted-by":"crossref","unstructured":"Jung K, Kim KI, Han J (2002a) Text extraction in real scene images on planar planes. In: 2002 International Conference on Pattern Recognition, vol. 3. IEEE, pp. 469\u2013472.","DOI":"10.1109\/ICPR.2002.1047978"},{"key":"20257_CR102","doi-asserted-by":"crossref","unstructured":"Jung K, Kim KI, Kurata T, Kourogi M, Han J (2002b) Text scanner with text detection technology on image sequences. In: 2002 International Conference on Pattern Recognition, vol. 3. IEEE, pp. 473\u2013476.","DOI":"10.1109\/ICPR.2002.1047979"},{"key":"20257_CR103","doi-asserted-by":"crossref","unstructured":"Kang L, Li Y, Doermann D (2014) Orientation robust text line detection in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4034\u20134041.","DOI":"10.1109\/CVPR.2014.514"},{"issue":"8","key":"20257_CR104","doi-asserted-by":"crossref","first-page":"3965","DOI":"10.1109\/TIP.2017.2707805","volume":"26","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu S, Tao R, van Gemert JC, Gevers T (2017) Con-text: Text detection for fine-grained object classification. IEEE Trans Image Process 26(8):3965\u20133980","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR105","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, Iwamura M, i Bigorda LG, Mestre SR, Mas J, Mota DF, Almazan JA, De Las Heras LP (2013) ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, IEEE, pp. 1484\u20131493.","DOI":"10.1109\/ICDAR.2013.221"},{"key":"20257_CR106","unstructured":"Kasar T, Ramakrishnan AG, Dharwadker A, Sharma A (2011) TexTraCC: Text extraction using color-based connected component labeling. In: Centenary Conference Electrical Engineering, Indian Institute of Science, pp. 1\u20135."},{"issue":"2","key":"20257_CR107","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s13735-016-0116-5","volume":"6","author":"A Kaur","year":"2017","unstructured":"Kaur A, Dhir R, Lehal GS (2017) A survey on camera-captured scene text detection and extraction: towards Gurmukhi script. Int J Multimed Inf Retr 6(2):115\u2013142","journal-title":"Int J Multimed Inf Retr"},{"key":"20257_CR108","doi-asserted-by":"crossref","unstructured":"Khlif W, Nayef N, Burie JC, Ogier JM, Alimi A (2018) Learning text component features via convolutional neural networks for scene text detection. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), IEEE, pp. 79\u201384.","DOI":"10.1109\/DAS.2018.65"},{"issue":"4","key":"20257_CR109","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1006\/jvci.1996.0029","volume":"7","author":"HK Kim","year":"1996","unstructured":"Kim HK (1996) Efficient automatic text location method and content-based indexing and structuring of video database. J Vis Commun Image Represent 7(4):336\u2013344","journal-title":"J Vis Commun Image Represent"},{"key":"20257_CR110","unstructured":"Kim JH, Lee S (2011) KAIST scene text database. Available at: http:\/\/www.iaprtc11.org\/mediawiki\/index.php\/KAIST_Scene_Text_Database. Accessed 11 Jan 2011"},{"key":"20257_CR111","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.ins.2018.04.092","volume":"460","author":"JY Kim","year":"2018","unstructured":"Kim JY, Bu SJ, Cho SB (2018) Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders. Inf Sci 460:83\u2013102","journal-title":"Inf Sci"},{"issue":"12","key":"20257_CR112","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1109\/TPAMI.2003.1251157","volume":"25","author":"KI Kim","year":"2003","unstructured":"Kim KI, Jung K, Kim JH (2003) Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm. IEEE Trans Pattern Anal Mach Intell 25(12):1631\u20131639","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"20257_CR113","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/TIP.2008.2008225","volume":"18","author":"W Kim","year":"2009","unstructured":"Kim W, Kim C (2009) A new approach for overlay text detection and extraction from complex video scene. IEEE Trans Image Process 18(2):401\u2013411","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"20257_CR114","doi-asserted-by":"crossref","first-page":"2296","DOI":"10.1109\/TIP.2013.2249082","volume":"22","author":"HI Koo","year":"2013","unstructured":"Koo HI, Kim DH (2013) Scene text detection via connected component clustering and nontext filtering. IEEE Trans Image Process 22(6):2296\u20132305","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR115","doi-asserted-by":"crossref","unstructured":"Koppula VK, Atul N, Garain U (2009) Robust text line, word and character extraction from Telugu document image. In: 2009 2nd International Conference on Emerging Trends in Engineering & Technology, IEEE, pp. 269\u2013272.","DOI":"10.1109\/ICETET.2009.196"},{"key":"20257_CR116","doi-asserted-by":"crossref","unstructured":"Kumar M, Kim YC, Lee GS (2010) Text detection using multilayer separation in real scene images. In: 2010 10th IEEE International Conference on Computer and Information Technology, IEEE, pp. 1413\u20131417.","DOI":"10.1109\/CIT.2010.253"},{"key":"20257_CR117","doi-asserted-by":"crossref","unstructured":"Lai AN, Lee G (2008) Binarization by local k-means clustering for Korean text extraction. In: 2008 IEEE International Symposium on Signal Processing and Information Technology, IEEE, pp. 117\u2013122.","DOI":"10.1109\/ISSPIT.2008.4775658"},{"issue":"3","key":"20257_CR118","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1016\/j.compeleceng.2012.09.015","volume":"39","author":"MA Lalimi","year":"2013","unstructured":"Lalimi MA, Ghofrani S, McLernon D (2013) A vehicle license plate detection method using region and edge based methods. Comput Electr Eng 39(3):834\u2013845","journal-title":"Comput Electr Eng"},{"key":"20257_CR119","unstructured":"Language and Media Processing (LAMP) (2003) Laboratory, media group, University of Maryland, College Park. http:\/\/www.umiacs.umd.edu\/lamp\/contact.htm. Accessed 29 Aug 2022"},{"issue":"01","key":"20257_CR120","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1142\/S0218001495000043","volume":"9","author":"CM Lee","year":"1995","unstructured":"Lee CM, Kankanhalli A (1995) Automatic extraction of characters in complex scene images. Int J Pattern Recognit Artif Intell 9(01):67\u201382","journal-title":"Int J Pattern Recognit Artif Intell"},{"issue":"10","key":"20257_CR121","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/34.541415","volume":"18","author":"SW Lee","year":"1996","unstructured":"Lee SW, Lee DJ, Park HS (1996) A new methodology for gray-scale character segmentation and recognition. IEEE Trans Pattern Anal Mach Intell 18(10):1045\u20131050","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR122","doi-asserted-by":"crossref","unstructured":"Lemaitre A, Camillerapp J (2006) Text line extraction in handwritten document with Kalman filter applied on low resolution image. In: 2nd International Conference on Document Image Analysis for Libraries (DIAL'06), IEEE, pp. 45\u201352.","DOI":"10.1109\/DIAL.2006.41"},{"issue":"1","key":"20257_CR123","first-page":"105","volume":"2","author":"CW Liang","year":"2004","unstructured":"Liang CW, Chen PY (2004) DWT based text localization. Int J Appl Sci Eng 2(1):105\u2013116","journal-title":"Int J Appl Sci Eng"},{"issue":"2","key":"20257_CR124","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10032-004-0138-z","volume":"7","author":"J Liang","year":"2005","unstructured":"Liang J, Doermann D, Li H (2005) Camera-based analysis of text and documents: a survey. IJDAR 7(2):84\u2013104","journal-title":"IJDAR"},{"issue":"8","key":"20257_CR125","doi-asserted-by":"crossref","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao M, Shi B, Bai X (2018) Textboxes++: A single-shot oriented scene text detector. IEEE Trans Image Process 27(8):3676\u20133690","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR126","first-page":"1","volume":"1","author":"G Liao","year":"2021","unstructured":"Liao G, Zhu Z, Bai Y, Liu T, Xie Z (2021) PSENet-based efficient scene text detection. EURASIP J Adv Signal Process 1:1\u201313","journal-title":"EURASIP J Adv Signal Process"},{"key":"20257_CR127","first-page":"363","volume-title":"International Workshop on Document Analysis Systems","author":"H Li","year":"1999","unstructured":"Li H, Doermann D, Kia O (1999) Text extraction, enhancement and OCR in digital video. International Workshop on Document Analysis Systems. Springer, Berlin, Heidelberg, pp 363\u2013377"},{"issue":"1","key":"20257_CR128","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/83.817607","volume":"9","author":"H Li","year":"2000","unstructured":"Li H, Doermann D, Kia O (2000) Automatic text detection and tracking in digital video. IEEE Trans Image Process 9(1):147\u2013156","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR129","doi-asserted-by":"crossref","unstructured":"Li H, Doermann D (2000b) A video text detection system based on automated training. In: Proceedings of 15th International Conference on Pattern Recognition. ICPR-2000, vol. 2. IEEE, pp. 223\u2013226.","DOI":"10.1109\/ICPR.2000.906053"},{"issue":"19","key":"20257_CR130","doi-asserted-by":"crossref","first-page":"10599","DOI":"10.3390\/app131910599","volume":"13","author":"J Li","year":"2023","unstructured":"Li J, Wu C (2023) Deep Learning and Text Mining: Classifying and Extracting Key Information from Construction Accident Narratives. Appl Sci 13(19):10599","journal-title":"Appl Sci"},{"issue":"21","key":"20257_CR131","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1093\/bioinformatics\/btz228","volume":"35","author":"P Li","year":"2019","unstructured":"Li P, Jiang X, Shatkay H (2019) Figure and caption extraction from biomedical documents. Bioinformatics 35(21):4381\u20134388","journal-title":"Bioinformatics"},{"key":"20257_CR132","doi-asserted-by":"crossref","first-page":"93998","DOI":"10.1109\/ACCESS.2019.2928364","volume":"7","author":"THS Li","year":"2019","unstructured":"Li THS, Kuo PH, Tsai TN, Luan PC (2019) CNN and LSTM based facial expression analysis model for a humanoid robot. IEEE Access 7:93998\u201394011","journal-title":"IEEE Access"},{"key":"20257_CR133","doi-asserted-by":"crossref","unstructured":"Li X, Guo S, Gao F (2006) Text extraction in video image based on Wavelet Modulus Maximum. In: 2006 IET International Conference on Wireless, Mobile and Multimedia Networks, IET, pp. 1\u20134.","DOI":"10.1049\/cp:20061477"},{"issue":"4","key":"20257_CR134","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1109\/TIP.2014.2302896","volume":"23","author":"Y Li","year":"2014","unstructured":"Li Y, Jia W, Shen C, van den Hengel A (2014) Characterness: an indicator of text in the wild. IEEE Trans Image Process 23(4):1666\u20131677","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR135","doi-asserted-by":"crossref","unstructured":"Lienhart RW, Stuber F (1996) Automatic text recognition in digital videos. In: Image and video processing IV, vol. 2666. SPIE, pp. 180\u2013188.","DOI":"10.1117\/12.234741"},{"issue":"1","key":"20257_CR136","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s005300050006","volume":"8","author":"R Lienhart","year":"2000","unstructured":"Lienhart R, Effelsberg W (2000) Automatic text segmentation and text recognition for video indexing. Multimedia Syst 8(1):69\u201381","journal-title":"Multimedia Syst"},{"key":"20257_CR137","first-page":"49","volume":"36","author":"MW Lin","year":"2006","unstructured":"Lin MW, Tapamo JR (2006) Ndovie B (2006) A texture-based method for document segmentation and classification. S Afr Comput J 36:49\u201356","journal-title":"S Afr Comput J"},{"key":"20257_CR138","doi-asserted-by":"crossref","first-page":"144341","DOI":"10.1109\/ACCESS.2021.3121608","volume":"9","author":"OY Ling","year":"2021","unstructured":"Ling OY, Theng LB, Weiyen AC, Mccarthy C (2021) Development of vertical text interpreter for natural scene images. IEEE Access 9:144341\u2013144351","journal-title":"IEEE Access"},{"key":"20257_CR139","doi-asserted-by":"crossref","unstructured":"Liu C, Wang C, Dai R (2005) Text detection in images based on unsupervised classification of edge-based features. In: 8th International Conference on Document Analysis and Recognition (ICDAR'05), IEEE, pp. 610\u2013614.","DOI":"10.1109\/ICDAR.2005.228"},{"key":"20257_CR140","doi-asserted-by":"crossref","first-page":"44219","DOI":"10.1109\/ACCESS.2019.2908933","volume":"7","author":"F Liu","year":"2019","unstructured":"Liu F, Chen C, Gu D, Zheng J (2019) FTPN: Scene text detection with feature pyramid based text proposal network. IEEE Access 7:44219\u201344228","journal-title":"IEEE Access"},{"issue":"10","key":"20257_CR141","doi-asserted-by":"crossref","first-page":"36","DOI":"10.4236\/jcc.2017.510005","volume":"5","author":"G Liu","year":"2017","unstructured":"Liu G, Jiang M, Cun H, Shi Z, Hao J (2017) An automatic text region positioning method for the low-contrast image. J Comput Commun 5(10):36\u201349","journal-title":"J Comput Commun"},{"key":"20257_CR142","first-page":"102","volume":"58","author":"M Liu","year":"2023","unstructured":"Liu M, Luo X, Wang G, Lu WZ (2023) Intelligent information extraction from government on-site inspection reports of construction projects: A graph-based text mining approach. Adv Eng Inform 58:102\u2013163","journal-title":"Adv Eng Inform"},{"key":"20257_CR143","doi-asserted-by":"crossref","unstructured":"Liu X, Samarabandu J (2005) An edge-based text region extraction algorithm for indoor mobile robot navigation. In: IEEE International Conference Mechatronics and Automation, vol. 2. IEEE, pp. 701\u2013706.","DOI":"10.1109\/ICMA.2005.1626635"},{"key":"20257_CR144","doi-asserted-by":"crossref","unstructured":"Liu X, Samarabandu J (2006) Multiscale edge-based text extraction from complex images. In: 2006 IEEE International Conference on Multimedia and Expo 2006, IEEE, pp. 1721\u20131724.","DOI":"10.1109\/ICME.2006.262882"},{"issue":"3","key":"20257_CR145","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1093\/ietisy\/e89-d.3.1221","volume":"89","author":"Y Liu","year":"2006","unstructured":"Liu Y, Goto S, Ikenaga T (2006) A contour-based robust algorithm for text detection in color images. IEICE Trans Inf Syst 89(3):1221\u20131230","journal-title":"IEICE Trans Inf Syst"},{"issue":"12","key":"20257_CR146","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.1016\/j.patcog.2008.12.016","volume":"42","author":"G Louloudis","year":"2009","unstructured":"Louloudis G, Gatos B, Pratikakis I, Halatsis C (2009) Text line and word segmentation of handwritten documents. Pattern Recogn 42(12):3169\u20133183","journal-title":"Pattern Recogn"},{"issue":"2","key":"20257_CR147","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s10032-015-0237-z","volume":"18","author":"S Lu","year":"2015","unstructured":"Lu S, Chen T, Tian S, Lim JH, Tan CL (2015) Scene text extraction based on edges and support vector regression. Int J Document Anal Recognit 18(2):125\u2013135","journal-title":"Int J Document Anal Recognit"},{"issue":"2","key":"20257_CR148","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/TCSVT.2004.841653","volume":"15","author":"MR Lyu","year":"2005","unstructured":"Lyu MR, Song J, Cai M (2005) A comprehensive method for multilingual video text detection, localization, and extraction. IEEE Trans Circuits Syst Video Technol 15(2):243\u2013255","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"20257_CR149","unstructured":"Ma D, Lin Q, Zhang T (2007) Mobile camera based text detection and translation. Department of Electrical Engg Stanford University."},{"issue":"11","key":"20257_CR150","doi-asserted-by":"crossref","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma J, Shao W, Ye H, Wang L, Wang H, Zheng Y, Xue X (2018) Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans Multimedia 20(11):3111\u20133122","journal-title":"IEEE Trans Multimedia"},{"key":"20257_CR151","doi-asserted-by":"crossref","unstructured":"Ma Z, He K, Wei Y, Sun J, Wu E (2013) Constant time weighted median filtering for stereo matching and beyond. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 49\u201356.","DOI":"10.1109\/ICCV.2013.13"},{"key":"20257_CR152","doi-asserted-by":"crossref","unstructured":"Mao J, Li H, Zhou W, Yan S, Tian Q (2013) Scale based region growing for scene text detection. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 1007\u20131016.","DOI":"10.1145\/2502081.2502108"},{"key":"20257_CR153","doi-asserted-by":"crossref","unstructured":"Mao W, Chung FL, Lam KK, Sun WC (2002) Hybrid Chinese\/English text detection in images and video frames. In: 2002 International Conference on Pattern Recognition, vol. 3. IEEE, pp. 1015\u20131018.","DOI":"10.1109\/ICPR.2002.1048210"},{"key":"20257_CR154","unstructured":"Madasu VK, Mohd. Hafizuddin Mohd. Yusof, Hanmandlu M, Kubik K (2003) Automatic extraction of signatures from bank cheques and other documents. In: DICTA, vol. 3. pp. 591\u2013600."},{"issue":"06","key":"20257_CR155","doi-asserted-by":"crossref","first-page":"2050052","DOI":"10.1142\/S0219691320500526","volume":"18","author":"F Makhmudov","year":"2020","unstructured":"Makhmudov F, Mukhiddinov M, Abdusalomov A, Avazov K, Khamdamov U, Cho YI (2020) Improvement of the end-to-end scene text recognition method for \u201ctext-to-speech\u201d conversion. Int J Wavelets Multiresolut Inf Process 18(06):2050052","journal-title":"Int J Wavelets Multiresolut Inf Process"},{"issue":"2","key":"20257_CR156","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1007\/s12065-019-00248-z","volume":"14","author":"VN Manjunath Aradhya","year":"2021","unstructured":"Manjunath Aradhya VN, Basavaraju HT, Guru DS (2021) Decade research on text detection in images\/videos: a review. Evol Intel 14(2):405\u2013431","journal-title":"Evol Intel"},{"key":"20257_CR157","doi-asserted-by":"publisher","unstructured":"Mandic DP, Chambers J (2001) Recurrent neural networks for prediction: learning algorithms, architectures and stability. John Wiley & Sons, Inc. https:\/\/doi.org\/10.1002\/047084535X","DOI":"10.1002\/047084535X"},{"key":"20257_CR158","doi-asserted-by":"crossref","unstructured":"Maruyama M, Yamaguchi T (2009) Extraction of characters on signboards in natural scene images by stump classifiers. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp. 1365\u20131369.","DOI":"10.1109\/ICDAR.2009.147"},{"issue":"5","key":"20257_CR159","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1016\/S0031-3203(98)00108-3","volume":"32","author":"S Messelodi","year":"1999","unstructured":"Messelodi S, Modena CM (1999) Automatic identification and skew estimation of text lines in real scene images. Pattern Recogn 32(5):791\u2013810","journal-title":"Pattern Recogn"},{"key":"20257_CR160","doi-asserted-by":"crossref","unstructured":"Minaee S, Wang Y (2017) Text extraction from texture images using masked signal decomposition. In: 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), IEEE, pp. 1210\u20131214.","DOI":"10.1109\/GlobalSIP.2017.8309153"},{"key":"20257_CR161","first-page":"1","volume":"1","author":"A Mirza","year":"2020","unstructured":"Mirza A, Zeshan O, Atif M (2020) Siddiqi I (2020) Detection and recognition of cursive text from video frames. EURASIP J Image Video Process 1:1\u20139","journal-title":"EURASIP J Image Video Process"},{"key":"20257_CR162","doi-asserted-by":"crossref","unstructured":"Mittal R, Garg A (2020) Text extraction using OCR: a systematic review. In: 2020 2nd International Conference on Inventive Research in Computing Applications (ICIRCA), IEEE, pp. 357\u2013362.","DOI":"10.1109\/ICIRCA48905.2020.9183326"},{"key":"20257_CR163","doi-asserted-by":"crossref","unstructured":"Mishra A, Alahari K, Jawahar CV (2012) Top-down and bottom-up cues for scene text recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 2687\u20132694.","DOI":"10.1109\/CVPR.2012.6247990"},{"issue":"2","key":"20257_CR164","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1049\/iet-ipr.2012.0441","volume":"7","author":"M Moradi","year":"2013","unstructured":"Moradi M, Mozaffari S (2013) Hybrid approach for Farsi\/Arabic text detection and localisation in video frames. IET Image Proc 7(2):154\u2013164","journal-title":"IET Image Proc"},{"issue":"02","key":"20257_CR165","first-page":"120","volume":"2","author":"P Nagabhushan","year":"2010","unstructured":"Nagabhushan P, Nirmala S (2010) Text extraction in complex color document images for enhanced readability. Intell Inf Manag 2(02):120\u2013133","journal-title":"Intell Inf Manag"},{"key":"20257_CR166","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1007\/978-3-642-29364-1_12","volume-title":"International Workshop on Camera-Based Document Analysis and Recognition","author":"R Nagy","year":"2012","unstructured":"Nagy R, Dicker A, Meyer-Wegener K (2012) NEOCR: A configurable dataset for natural image text recognition. International Workshop on Camera-Based Document Analysis and Recognition. Springer, Berlin, Heidelberg, pp 150\u2013163"},{"key":"20257_CR167","first-page":"11798","volume":"4","author":"G Nagaraju","year":"2015","unstructured":"Nagaraju G, Ramaraju PV, Sandeep PM, Nawaz SM, Bhargav SK (2015) Text extraction from images with edge-enhanced MSER and hardware interfacing using Arduino. Int J Eng Comput Sci 4:11798\u201311803","journal-title":"Int J Eng Comput Sci"},{"key":"20257_CR168","doi-asserted-by":"publisher","unstructured":"Naveed H, Khan AU, Qiu S, Saqib M, Anwar S, Usman M, Akhtar N, Barnes N, Mian A (2023) A comprehensive overview of large language models. https:\/\/doi.org\/10.48550\/arXiv.2307.06435.","DOI":"10.48550\/arXiv.2307.06435"},{"key":"20257_CR169","first-page":"770","volume-title":"Asian conference on computer vision","author":"L Neumann","year":"2010","unstructured":"Neumann L, Matas J (2010) A method for text localization and recognition in real-world images. Asian conference on computer vision. Springer, Berlin, Heidelberg, pp 770\u2013783"},{"key":"20257_CR170","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2012) Real-time scene text localization and recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 3538\u20133545.","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"20257_CR171","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2011) Text localization in real-world images using efficiently pruned exhaustive search. In: 2011 International conference on document analysis and recognition, IEEE, pp. 687\u2013691.","DOI":"10.1109\/ICDAR.2011.144"},{"key":"20257_CR172","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2013) Scene text localization and recognition with oriented stroke detection. In: Proceedings of the IEEE International conference on computer vision, pp. 97\u2013104.","DOI":"10.1109\/ICCV.2013.19"},{"key":"20257_CR173","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2015) Efficient scene text localization and recognition with local character refinement. In: 2015 13th International conference on document analysis and recognition (ICDAR), IEEE, pp. 746\u2013750.","DOI":"10.1109\/ICDAR.2015.7333861"},{"issue":"9","key":"20257_CR174","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1109\/TPAMI.2015.2496234","volume":"38","author":"L Neumann","year":"2016","unstructured":"Neumann L, Matas J (2016) Real-time lexicon-free scene text localization and recognition. IEEE Trans Pattern Anal Mach Intell 38(9):1872\u20131885","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR175","doi-asserted-by":"crossref","unstructured":"Ning G, Han TX, He Z (2015) Scene text detection based on component-level fusion and region-level verification. In: 2015 IEEE international conference on image processing (ICIP), IEEE, pp. 837\u2013841.","DOI":"10.1109\/ICIP.2015.7350917"},{"key":"20257_CR176","first-page":"752","volume-title":"European conference on computer vision","author":"T Novikova","year":"2012","unstructured":"Novikova T, Barinova O, Kohli P, Lempitsky V (2012) Large-lexicon attribute-consistent text recognition in natural images. European conference on computer vision. Springer, Berlin, Heidelberg, pp 752\u2013765"},{"issue":"2","key":"20257_CR177","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/34.273729","volume":"16","author":"J Ohya","year":"1994","unstructured":"Ohya J, Shio A, Akamatsu S (1994) Recognizing characters in scene images. IEEE Trans Pattern Anal Mach Intell 16(2):214\u2013220","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"20257_CR178","first-page":"1418","volume":"1","author":"S Ozbay","year":"2007","unstructured":"Ozbay S, Ercelebi E (2007) Automatic vehicle identification by plate recognition. Int J Comput Inform Eng 1(9):1418\u20131421","journal-title":"Int J Comput Inform Eng"},{"key":"20257_CR179","doi-asserted-by":"crossref","unstructured":"Pan YF, Hou X, Liu CL (2009) Text localization in natural scene images based on conditional random field. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp. 6\u201310.","DOI":"10.1109\/ICDAR.2009.97"},{"key":"20257_CR180","doi-asserted-by":"crossref","unstructured":"Pan YF, Liu CL, Hou X (2010a) Fast scene text localization by learning-based filtering and verification. In: 2010 IEEE international conference on image processing, IEEE, pp. 2269\u20132272.","DOI":"10.1109\/ICIP.2010.5651862"},{"issue":"3","key":"20257_CR181","first-page":"800","volume":"20","author":"YF Pan","year":"2010","unstructured":"Pan YF, Hou X, Liu CL (2010) A hybrid approach to detect and localize texts in natural scene images. IEEE Trans Image Process 20(3):800\u2013813","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"20257_CR182","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41133-021-00051-5","volume":"6","author":"BK Pandey","year":"2021","unstructured":"Pandey BK, Pandey D, Wariya S, Aggarwal G, Rastogi R (2021) Deep learning and particle swarm optimisation-based techniques for visually impaired humans\u2019 text recognition and identification. Augment Hum Res 6(1):1\u201314","journal-title":"Augment Hum Res"},{"issue":"12","key":"20257_CR183","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.1016\/j.patrec.2010.05.024","volume":"31","author":"J Park","year":"2010","unstructured":"Park J, Lee G, Kim E, Lim J, Kim S, Yang H, Lee M, Hwang S (2010) Automatic detection and recognition of Korean text in outdoor signboard images. Pattern Recogn Lett 31(12):1728\u20131739","journal-title":"Pattern Recogn Lett"},{"issue":"17","key":"20257_CR184","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1049\/el:19990977","volume":"35","author":"SH Park","year":"1999","unstructured":"Park SH, Kim KI, Jung K, Kim HJ (1999) Locating car license plates using neural networks. Electron Lett 35(17):1475\u20131477","journal-title":"Electron Lett"},{"issue":"2","key":"20257_CR185","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s100320050038","volume":"2","author":"P Parodi","year":"1999","unstructured":"Parodi P, Fontana R (1999) Efficient and flexible text extraction from document pages. Int J Doc Anal Recogn 2(2):67\u201379","journal-title":"Int J Doc Anal Recogn"},{"key":"20257_CR186","doi-asserted-by":"crossref","first-page":"14630","DOI":"10.1109\/ACCESS.2019.2963702","volume":"8","author":"HT Phan","year":"2020","unstructured":"Phan HT, Tran VC, Nguyen NT, Hwang D (2020) Improving the performance of sentiment analysis of tweets containing fuzzy sentiment using the feature ensemble model. IEEE Access 8:14630\u201314641","journal-title":"IEEE Access"},{"key":"20257_CR187","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Tan CL (2009) A Laplacian method for video text detection. In: 2009 10th International conference on document analysis and recognition. IEEE, pp. 66\u201370.","DOI":"10.1109\/ICDAR.2009.153"},{"key":"20257_CR188","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Tian S, Tan CL (2013) Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 569\u2013576.","DOI":"10.1109\/ICCV.2013.76"},{"key":"20257_CR189","unstructured":"Praktische Informatik IV (2003) MoCA Project, http:\/\/www.informatik.unimannheim.de\/informatik\/pi4\/projects\/MoCA."},{"key":"20257_CR190","doi-asserted-by":"crossref","unstructured":"Qiao YL, Li M, Lu ZM, Sun SH (2006) Gabor filter based text extraction from digital document images. In: 2006 International Conference on Intelligent Information Hiding and Multimedia, IEEE, pp. 297\u2013300.","DOI":"10.1109\/IIH-MSP.2006.265002"},{"key":"20257_CR191","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.neucom.2021.09.022","volume":"466","author":"M Ragab","year":"2021","unstructured":"Ragab M, Chen Z, Wu M, Kwoh CK, Yan R, Li X (2021) Attention-based sequence to sequence model for machine remaining useful life prediction. Neurocomputing 466:58\u201368","journal-title":"Neurocomputing"},{"issue":"4","key":"20257_CR192","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TCSVT.2018.2817642","volume":"29","author":"KS Raghunandan","year":"2019","unstructured":"Raghunandan KS, Shivakumara P, Roy S, Kumar GH, Pal U, Lu T (2019) Multi-script-oriented text detection and recognition in video\/scene\/born digital images. IEEE Trans Circuits Syst Video Technol 29(4):1145\u20131162","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"4","key":"20257_CR193","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s42979-023-01776-3","volume":"4","author":"P Raghavendra Nayaka","year":"2023","unstructured":"Raghavendra Nayaka P, Ranjan R (2023) An efficient framework for algorithmic metadata extraction over scholarly documents using deep neural networks. SN Comput Sci 4(4):341","journal-title":"SN Comput Sci"},{"key":"20257_CR194","doi-asserted-by":"crossref","unstructured":"Rajan V, Raj S (2017) Text detection and character extraction in natural scene images using fractional Poisson model. In: 2017 International Conference on Computing Methodologies and Communication (ICCMC), IEEE, pp. 1136\u20131141.","DOI":"10.1109\/ICCMC.2017.8282651"},{"key":"20257_CR195","doi-asserted-by":"crossref","unstructured":"Raju SS, Pati PB, Ramakrishnan AG (2004) Gabor filter based block energy analysis for text extraction from digital document images. In: First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings, IEEE, pp. 233\u2013243.","DOI":"10.1109\/DIAL.2004.1263252"},{"key":"20257_CR196","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/978-3-030-50641-4_6","volume-title":"Machine learning algorithms for industrial applications","author":"A Ranjan","year":"2021","unstructured":"Ranjan A, Behera VN, Reza M (2021) OCR using computer vision and machine learning. Machine learning algorithms for industrial applications. Springer, Cham, pp 83\u2013105"},{"key":"20257_CR197","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"key":"20257_CR198","unstructured":"Reina AV, Sastre RL, Arroyo SL, Jim\u00e9nez PG (2006) Adaptive traffic road sign panels text extraction. In: Proceedings of 5th WSEAS International Conference on Signal Processing, Robotics and Automation. World Scientific and Engineering Academy and Society (WSEAS), pp. 295\u2013300."},{"key":"20257_CR199","doi-asserted-by":"crossref","unstructured":"Ren X, Chen K, Yang X, Zhou Y, He J, Sun J (2016) A novel scene text detection algorithm based on convolutional neural network. In: 2016 Visual Communications and Image Processing (VCIP), IEEE, pp. 1\u20134.","DOI":"10.1109\/VCIP.2016.7805444"},{"issue":"3","key":"20257_CR200","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1109\/TMM.2016.2625259","volume":"19","author":"X Ren","year":"2017","unstructured":"Ren X, Zhou Y, He J, Chen K, Yang X, Sun J (2017) A convolutional neural network-based Chinese text detection algorithm via text structure modeling. IEEE Trans Multimedia 19(3):506\u2013518","journal-title":"IEEE Trans Multimedia"},{"key":"20257_CR201","doi-asserted-by":"crossref","first-page":"3193","DOI":"10.1109\/ACCESS.2017.2676158","volume":"5","author":"X Ren","year":"2017","unstructured":"Ren X, Zhou Y, Huang Z, Sun J, Yang X, Chen K (2017) A novel text structure feature extractor for Chinese scene text detection and recognition. IEEE Access 5:3193\u20133204","journal-title":"IEEE Access"},{"key":"20257_CR202","doi-asserted-by":"crossref","unstructured":"Saeedi J, Safabakhsh R, Mozaffari S (2009) Document image segmentation using fuzzy classifier and the dual-tree DWT. In: 2009 14th International CSI Computer Conference, IEEE, pp. 385\u2013391.","DOI":"10.1109\/CSICC.2009.5349611"},{"issue":"2","key":"20257_CR203","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1080\/02564602.2016.1160805","volume":"34","author":"P Sahare","year":"2017","unstructured":"Sahare P, Dhok SB (2017) Review of text extraction algorithms for scene-text and document images. IETE Tech Rev 34(2):144\u2013164","journal-title":"IETE Tech Rev"},{"key":"20257_CR204","doi-asserted-by":"crossref","unstructured":"Sahota KK, Awasthi LK, Verma HK (2017) An empirical enhancement using scale invariant feature transform in text extraction from images. In: 2017 International Conference on Intelligent Communication and Computational Techniques (ICCT), IEEE, pp. 228\u2013232.","DOI":"10.1109\/INTELCCT.2017.8324050"},{"key":"20257_CR205","doi-asserted-by":"crossref","unstructured":"Saoi T, Goto H, Kobayashi H (2005) Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features. In: 8th International Conference on Document Analysis and Recognition (ICDAR'05), IEEE, pp. 690\u2013694.","DOI":"10.1109\/ICDAR.2005.227"},{"issue":"6","key":"20257_CR206","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/s42979-021-00815-1","volume":"2","author":"IH Sarker","year":"2021","unstructured":"Sarker IH (2021) Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput Sci 2(6):420","journal-title":"SN Comput Sci"},{"issue":"2","key":"20257_CR207","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1007\/s42979-022-01043-x","volume":"3","author":"IH Sarker","year":"2022","unstructured":"Sarker IH (2022) AI-based modeling: techniques, applications and research issues towards automation, intelligent and smart systems. SN Comput Sci 3(2):158","journal-title":"SN Comput Sci"},{"key":"20257_CR208","doi-asserted-by":"crossref","unstructured":"Sarkar R, Halder S, Malakar S, Das N, Basu S, Nasipuri M (2012) Text line extraction from handwritten document pages based on line contour estimation. In: 2012 3rd International Conference on Computing, Communication and Networking Technologies (ICCCNT'12), IEEE, pp. 1\u20138.","DOI":"10.1109\/ICCCNT.2012.6395873"},{"key":"20257_CR209","doi-asserted-by":"crossref","unstructured":"Sato T, Kanade T, Hughes EK, Smith MA (1998) Video OCR for digital news archive. In: Proceedings of 1998 IEEE International Workshop on Content-Based Access of Image and Video Database, IEEE, pp. 52\u201360.","DOI":"10.1109\/CAIVD.1998.646033"},{"key":"20257_CR210","doi-asserted-by":"crossref","unstructured":"Seeri SV, Giraddi S, Prashant BM (2012) A novel approach for Kannada text extraction. In: International Conference on Pattern Recognition, Informatics and Medical Engineering (PRIME-2012), IEEE, pp. 444\u2013448.","DOI":"10.1109\/ICPRIME.2012.6208387"},{"key":"20257_CR211","doi-asserted-by":"crossref","unstructured":"Shah S, Modi C, Patel M (2011) Novel approach for text extraction from natural images using ISEF edge detection. In: 2011 International Conference on Emerging Trends in Networks and Computer Communications (ETNCC), IEEE, pp. 487\u2013491.","DOI":"10.1109\/ETNCC.2011.6255887"},{"issue":"3","key":"20257_CR212","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1016\/j.patcog.2014.09.012","volume":"48","author":"N Sharma","year":"2015","unstructured":"Sharma N, Shivakumara P, Pal U, Blumenstein M, Tan CL (2015) Piece-wise linearity based method for text frame classification in video. Pattern Recogn 48(3):862\u2013881","journal-title":"Pattern Recogn"},{"key":"20257_CR213","doi-asserted-by":"crossref","unstructured":"Shang H, Wang L, Hiroshi T, Fan W, Sun J, Naoi S (2016) Character region segmentation based on stroke stable regions. In: 2016 23rd International Conference on Pattern Recognition (ICPR), IEEE, pp. 3975\u20133980.","DOI":"10.1109\/ICPR.2016.7900255"},{"key":"20257_CR214","doi-asserted-by":"crossref","unstructured":"Shekar BH, Smitha ML, Shivakumara P (2014) Discrete wavelet transform and gradient difference based approach for text localization in videos. In: 2014 5th International Conference on Signal and Image Processing, IEEE, pp. 280\u2013284.","DOI":"10.1109\/ICSIP.2014.50"},{"key":"20257_CR215","doi-asserted-by":"crossref","unstructured":"Shekar BH, Smitha ML (2015a) Text localization in video\/scene images using Kirsch Directional Masks. In: 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, pp. 1436\u20131440.","DOI":"10.1109\/ICACCI.2015.7275814"},{"key":"20257_CR216","doi-asserted-by":"crossref","unstructured":"Shekar BH, Smitha ML (2015b) Phase congruency and morphology based approach for text localization in videos. In: 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, pp. 2221\u20132225.","DOI":"10.1109\/ICACCI.2015.7275947"},{"issue":"11","key":"20257_CR217","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi B, Bai X, Yao C (2017) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298\u20132304","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR218","doi-asserted-by":"crossref","unstructured":"Shi B, Wang X, Lyu P, Yao C, Bai X (2016) Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4168\u20134176).","DOI":"10.1109\/CVPR.2016.452"},{"issue":"2","key":"20257_CR219","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.patrec.2012.09.019","volume":"34","author":"C Shi","year":"2013","unstructured":"Shi C, Wang C, Xiao B, Zhang Y, Gao S (2013) Scene text detection using graph model built upon maximally stable extremal regions. Pattern Recogn Lett 34(2):107\u2013116","journal-title":"Pattern Recogn Lett"},{"key":"20257_CR220","doi-asserted-by":"crossref","unstructured":"Shi Z, Setlur S, Govindaraju V (2005) Text extraction from gray scale historical document images using adaptive local connectivity map. In: 8th International Conference on Document Analysis and Recognition (ICDAR'05), IEEE, pp. 794\u2013798.","DOI":"10.1109\/ICDAR.2005.229"},{"key":"20257_CR221","doi-asserted-by":"crossref","unstructured":"Shi Z, Setlur S, Govindaraju V (2009) A steerable directional local profile technique for extraction of handwritten Arabic text lines. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp. 176\u2013180.","DOI":"10.1109\/ICDAR.2009.79"},{"key":"20257_CR222","doi-asserted-by":"crossref","unstructured":"Shim JC, Dorai C, Bolle R (1998) Automatic text extraction from video for content-based annotation and retrieval. In: Proceedings of 14th International Conference on Pattern Recognition (Cat. No. 98EX170), vol. 1. IEEE, pp. 618\u2013620.","DOI":"10.1109\/ICPR.1998.711219"},{"key":"20257_CR223","doi-asserted-by":"crossref","unstructured":"Shin CS, Kim KI, Park MH, Kim HJ (2000) Support vector machine-based text detection in digital video. In: Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No. 00TH8501), vol. 2. IEEE, pp. 634\u2013641.","DOI":"10.1109\/NNSP.2000.890142"},{"key":"20257_CR224","doi-asserted-by":"crossref","unstructured":"Shivakumara P, Phan TQ, Tan CL (2009a) Video text detection based on filters and edge features. In: 2009 IEEE International Conference on Multimedia and Expo, IEEE, pp. 514\u2013517.","DOI":"10.1109\/ICME.2009.5202546"},{"key":"20257_CR225","doi-asserted-by":"crossref","unstructured":"Shivakumara P, Phan TQ, Tan CL (2009b) A gradient difference based technique for video text detection. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp. 156\u2013160.","DOI":"10.1109\/ICDAR.2009.85"},{"issue":"6","key":"20257_CR226","doi-asserted-by":"crossref","first-page":"2165","DOI":"10.1016\/j.patcog.2010.01.009","volume":"43","author":"P Shivakumara","year":"2010","unstructured":"Shivakumara P, Huang W, Phan TQ, Tan CL (2010) Accurate video text detection through classification of low and high contrast images. Pattern Recogn 43(6):2165\u20132185","journal-title":"Pattern Recogn"},{"issue":"2","key":"20257_CR227","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TPAMI.2010.166","volume":"33","author":"P Shivakumara","year":"2011","unstructured":"Shivakumara P, Phan TQ, Tan CL (2011) A Laplacian approach to multi-oriented text detection in video. IEEE Trans Pattern Anal Mach Intell 33(2):412\u2013419","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR228","doi-asserted-by":"crossref","unstructured":"Sin BK, Kim SK, Cho BJ (2002) Locating characters in scene images using frequency features. In: Object Recognition Supported by User Interaction for Service Robots, vol. 3. IEEE, pp. 489\u2013492.","DOI":"10.1109\/ICPR.2002.1047983"},{"key":"20257_CR229","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1016\/j.procs.2024.04.141","volume":"235","author":"V Singh","year":"2024","unstructured":"Singh V, Bolla BK (2024) Hybrid Approach To Unsupervised Keyphrase Extraction. Procedia Comput Sci. 235:1498\u20131511. https:\/\/doi.org\/10.1016\/j.procs.2024.04.141","journal-title":"Procedia Comput Sci."},{"key":"20257_CR230","volume-title":"Video skimming for quick browsing based on audio and image characterization","author":"MA Smith","year":"1995","unstructured":"Smith MA, Kanade T (1995) Video skimming for quick browsing based on audio and image characterization. School of Computer Science, Carnegie Mellon University, Pittsburgh"},{"key":"20257_CR231","doi-asserted-by":"crossref","unstructured":"Sobottka K, Bunke H, Kronenberg H (1999) Identification of text on colored book and journal covers. In: Proceedings of the 5th International Conference on Document Analysis and Recognition. ICDAR'99 (Cat. No. PR00318), IEEE, pp. 57\u201362.","DOI":"10.1109\/ICDAR.1999.791724"},{"issue":"7","key":"20257_CR232","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1109\/TCSVT.2017.2671899","volume":"28","author":"T Song","year":"2018","unstructured":"Song T, Li H, Meng F, Wu Q, Cai J (2018) LETRIST: Locally encoded transform feature histogram for rotation-invariant texture classification. IEEE Trans Circuits Syst Video Technol 28(7):1565\u20131579","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"8","key":"20257_CR233","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1016\/S0031-3203(01)00167-4","volume":"35","author":"C Strouthopoulos","year":"2002","unstructured":"Strouthopoulos C, Papamarkos N, Atsalakis AE (2002) Text extraction in complex color documents. Pattern Recogn 35(8):1743\u20131758","journal-title":"Pattern Recogn"},{"key":"20257_CR234","doi-asserted-by":"crossref","unstructured":"Su YM, Hsieh CH (2006a) A novel caption extraction scheme for various sports captions. In: 18th International Conference on Pattern Recognition (ICPR'06), vol. 2. IEEE, pp. 1054\u20131057.","DOI":"10.1109\/ICPR.2006.135"},{"key":"20257_CR235","doi-asserted-by":"crossref","unstructured":"Su YM, Hsieh CH (2006b) A novel model-based segmentation approach to extract caption contents on sports videos. In: 2006 IEEE International Conference on Multimedia and Expo, IEEE, pp. 1829\u20131832.","DOI":"10.1109\/ICME.2006.262909"},{"issue":"4","key":"20257_CR236","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1049\/ip-vis:19960325","volume":"143","author":"HM Suen","year":"1996","unstructured":"Suen HM, Wang JF (1996) Text string extraction from images of colour-printed documents. IEEE Proceed Vision Image Signal Process 143(4):210\u2013216","journal-title":"IEEE Proceed Vision Image Signal Process"},{"key":"20257_CR237","doi-asserted-by":"crossref","first-page":"27","DOI":"10.5121\/ijcses.2012.3403","volume":"3","author":"CP Sumathi","year":"2012","unstructured":"Sumathi CP, Santhanam T, Devi GG (2012) A survey on various approaches of text extraction in images. Int J Comput Sci Eng Survey 3:27\u201342","journal-title":"Int J Comput Sci Eng Survey"},{"key":"20257_CR238","doi-asserted-by":"crossref","unstructured":"Sun L, Liu G, Qian X, Guo D (2009) A novel text detection and localization method based on corner response. In: 2009 IEEE International Conference on Multimedia and Expo, IEEE, pp. 390\u2013393.","DOI":"10.1109\/ICME.2009.5202516"},{"key":"20257_CR239","doi-asserted-by":"crossref","unstructured":"Tabassum A, Dhondse SA (2015) Text detection using MSER and stroke width transform. In: 2015 5th International Conference on Communication Systems and Network Technologies, IEEE, pp. 568\u2013571.","DOI":"10.1109\/CSNT.2015.154"},{"issue":"3","key":"20257_CR240","doi-asserted-by":"crossref","first-page":"105","DOI":"10.5897\/SRE2014.6146","volume":"10","author":"K Tahani","year":"2015","unstructured":"Tahani K, Huda K, Hiba M, Lama R (2015) A hybrid multilevel text extraction algorithm in scene images. Sci Res Essays 10(3):105\u2013113","journal-title":"Sci Res Essays"},{"key":"20257_CR241","doi-asserted-by":"crossref","unstructured":"Takahashi H, Nakajima M (2005) Region graph based text extraction from outdoor images. In: Third International Conference on Information Technology and Applications (ICITA'05), vol. 1. IEEE, pp. 680\u2013685.","DOI":"10.1109\/ICITA.2005.235"},{"key":"20257_CR242","doi-asserted-by":"crossref","unstructured":"Tang Y, Wu X (2016) Scene text detection via edge cue and multi-features. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), IEEE, pp. 156\u2013161.","DOI":"10.1109\/ICFHR.2016.0040"},{"issue":"3","key":"20257_CR243","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1109\/TIP.2017.2656474","volume":"26","author":"Y Tang","year":"2017","unstructured":"Tang Y, Wu X (2017) Scene text detection and segmentation based on cascaded convolution neural networks. IEEE Trans Image Process 26(3):1509\u20131520","journal-title":"IEEE Trans Image Process"},{"issue":"9","key":"20257_CR244","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1109\/TMM.2018.2802644","volume":"20","author":"Y Tang","year":"2018","unstructured":"Tang Y, Wu X (2018) Scene text detection using superpixel-based stroke feature transform and deep learning based region classification. IEEE Trans Multimedia 20(9):2276\u20132288","journal-title":"IEEE Trans Multimedia"},{"key":"20257_CR245","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2014\/389547","volume":"2014","author":"S Tehsin","year":"2014","unstructured":"Tehsin S, Masood A, Kausar S, Arif F (2014) Fuzzy-based segmentation for variable font-sized text extraction from images\/videos. Math Probl Eng 2014:1\u201310","journal-title":"Math Probl Eng"},{"issue":"01","key":"20257_CR246","doi-asserted-by":"crossref","first-page":"1555003","DOI":"10.1142\/S0218001415550034","volume":"29","author":"S Tehsin","year":"2015","unstructured":"Tehsin S, Masood A, Kausar S, Javed Y (2015) A caption text detection method from images\/videos for efficient indexing and retrieval of multimedia data. Int J Pattern Recognit Artif Intell 29(01):1555003","journal-title":"Int J Pattern Recognit Artif Intell"},{"key":"20257_CR247","doi-asserted-by":"publisher","unstructured":"Thakur N, Ghai D, Kumar S (2023) Automatic imagery Bank Cheque data extraction based on machine learning approaches: a comprehensive survey. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-023-14534-7","DOI":"10.1007\/s11042-023-14534-7"},{"key":"20257_CR248","doi-asserted-by":"crossref","unstructured":"Tian S, Pan Y, Huang C, Lu S, Yu K, Tan CL (2015) Text flow: a unified text detection system in natural scene images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4651\u20134659.","DOI":"10.1109\/ICCV.2015.528"},{"issue":"3","key":"20257_CR249","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1109\/TPAMI.2017.2692763","volume":"40","author":"S Tian","year":"2018","unstructured":"Tian S, Yin XC, Su Y, Hao HW (2018) A unified framework for tracking based text detection and recognition from web videos. IEEE Trans Pattern Anal Mach Intell 40(3):542\u2013554","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR250","doi-asserted-by":"crossref","unstructured":"Tounsi M, Moalla I, Alimi AM, Lebouregois F (2015) Arabic characters recognition in natural scenes using sparse coding for feature representations. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 1036\u20131040.","DOI":"10.1109\/ICDAR.2015.7333919"},{"issue":"1","key":"20257_CR251","first-page":"1","volume":"14","author":"TS Tung","year":"2018","unstructured":"Tung TS, Lee G (2018) Deep-learning approach for text detection using fully convolutional networks. Int J Contents 14(1):1\u20136","journal-title":"Int J Contents"},{"issue":"3","key":"20257_CR252","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1049\/iet-ipr.2018.5277","volume":"13","author":"S Unar","year":"2019","unstructured":"Unar S, Wang X, Zhang C, Wang C (2019) Detected text-based image retrieval approach for textual images. IET Image Proc 13(3):515\u2013521","journal-title":"IET Image Proc"},{"key":"20257_CR253","doi-asserted-by":"crossref","unstructured":"Van DN, Lu S, Bai X, Ouarti N, Mokhtari M (2017) Max-pooling based scene text proposal for scene text detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1. IEEE, pp. 1295\u20131300.","DOI":"10.1109\/ICDAR.2017.213"},{"key":"20257_CR254","doi-asserted-by":"crossref","unstructured":"Vellingiriraj EK, Balamurugan M, Balasubramanie P (2016) Information extraction and text mining of Ancient Vattezhuthu characters in historical documents using image zoning. In: 2016 International Conference on Asian Language Processing (IALP), IEEE, pp. 37\u201340.","DOI":"10.1109\/IALP.2016.7875929"},{"key":"20257_CR255","doi-asserted-by":"publisher","unstructured":"Veit A, Matera T, Neumann L, Matas J, Belongie S (2016) COCO-Text: Dataset and benchmark for text detection and recognition in natural images. https:\/\/doi.org\/10.48550\/arXiv.1601.07140.","DOI":"10.48550\/arXiv.1601.07140"},{"issue":"1","key":"20257_CR256","first-page":"1","volume":"15","author":"V Vijayakumar","year":"2011","unstructured":"Vijayakumar V, Nedunchezhian R (2011) A novel method for super imposed text extraction in a sports video. Int J Comput Appl 15(1):1\u20136","journal-title":"Int J Comput Appl"},{"key":"20257_CR257","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-3-030-57907-4_6","volume-title":"Digital techniques for heritage presentation and preservation","author":"M Wadhwani","year":"2021","unstructured":"Wadhwani M, Kundu D, Chakraborty D, Chanda B (2021) Text extraction and restoration of old handwritten documents. Digital techniques for heritage presentation and preservation. Springer, Cham, pp 109\u2013132"},{"key":"20257_CR258","doi-asserted-by":"crossref","unstructured":"Wang C, Yin F, Liu CL (2017) Scene text detection with novel superpixel based character candidate extraction. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, IEEE, pp. 929\u2013934.","DOI":"10.1109\/ICDAR.2017.156"},{"key":"20257_CR259","unstructured":"Wang H, Kangas J (2001a) Character-like region verification for extracting text in scene images. In: Proceedings of 6th International Conference on Document Analysis and Recognition, IEEE, pp. 957\u2013962."},{"key":"20257_CR260","unstructured":"Wang H (2001b) Automatic character location and segmentation in color scene images. In: Proceedings of 11th International Conference on Image Analysis and Processing, IEEE, pp. 2\u20137."},{"key":"20257_CR261","doi-asserted-by":"crossref","unstructured":"Wang J, Sun G, Wang P, Liu D, Dianat S, Rabbani M, Rao R, Tao Z (2024) Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, pp. 16551\u201316560.","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"20257_CR262","unstructured":"Wang K (2014) The street view text dataset (SVT). Available at: http:\/\/tc11.cvc.uab.es\/datasets\/SVT_1. Accessed 13 Jan 2014"},{"key":"20257_CR263","first-page":"591","volume-title":"European conference on computer vision","author":"K Wang","year":"2010","unstructured":"Wang K, Belongie S (2010) Word spotting in the wild. European conference on computer vision. Springer, Berlin, Heidelberg, pp 591\u2013604"},{"issue":"10","key":"20257_CR264","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1016\/S0031-3203(03)00082-7","volume":"36","author":"K Wang","year":"2003","unstructured":"Wang K, Kangas JA (2003) Character location in scene images from digital camera. Pattern Recogn 36(10):2287\u20132299","journal-title":"Pattern Recogn"},{"key":"20257_CR265","doi-asserted-by":"crossref","unstructured":"Wang Q, Lu Y, Wen Y (2015) Scene text detection using sequential nontext filtering. In: 2015 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 1742\u20131746.","DOI":"10.1109\/ICIP.2015.7351099"},{"key":"20257_CR266","doi-asserted-by":"crossref","unstructured":"Wang Q, Fang Y, Ravula A, Feng F, Quan X, Liu D (2022) Webformer: The web-page transformer for structure information extraction. In: Proceedings of the ACM Web Conference 2022, pp. 3124\u20133133.","DOI":"10.1145\/3485447.3512032"},{"key":"20257_CR267","doi-asserted-by":"crossref","unstructured":"Wang Q, Wang J, Quan X, Feng F, Xu Z, Nie S, Wang S, Khabsa M, Firooz H, Liu D (2023) MUSTIE: Multimodal structural transformer for web information extraction. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2405\u20132420.","DOI":"10.18653\/v1\/2023.acl-long.135"},{"key":"20257_CR268","unstructured":"Wang T, Wu DJ, Coates A, Ng AY (2012) End-to-end text recognition with convolutional neural networks. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), IEEE, pp. 3304\u20133308."},{"key":"20257_CR269","doi-asserted-by":"crossref","first-page":"160050","DOI":"10.1109\/ACCESS.2020.3020621","volume":"8","author":"Y Wang","year":"2020","unstructured":"Wang Y (2020) Extraction algorithm of English text information from color images based on radial wavelet transform. IEEE Access 8:160050\u2013160064","journal-title":"IEEE Access"},{"issue":"4","key":"20257_CR270","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1016\/j.eswa.2010.08.106","volume":"38","author":"YR Wang","year":"2011","unstructured":"Wang YR, Lin WH, Horng SJ (2011) A sliding window technique for efficient license plate localization based on discrete wavelet transform. Expert Syst Appl 38(4):3142\u20133146","journal-title":"Expert Syst Appl"},{"issue":"2","key":"20257_CR271","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1109\/TPAMI.2013.126","volume":"36","author":"JJ Weinman","year":"2014","unstructured":"Weinman JJ, Butler Z, Knoll D, Feild J (2014) Toward integrated scene text reading. IEEE Trans Pattern Anal Mach Intell 36(2):375\u2013387","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"20257_CR272","first-page":"309","volume":"6","author":"C Wolf","year":"2004","unstructured":"Wolf C, Jolion JM (2004) Extraction and recognition of artificial text in multimedia documents. Formal Pattern Anal Appl 6(4):309\u2013326","journal-title":"Formal Pattern Anal Appl"},{"issue":"8","key":"20257_CR273","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TMM.2015.2443556","volume":"17","author":"L Wu","year":"2015","unstructured":"Wu L, Shivakumara P, Lu T, Tan CL (2015) A new technique for multi-oriented scene text line detection and tracking in video. IEEE Trans Multimedia 17(8):1137\u20131152","journal-title":"IEEE Trans Multimedia"},{"key":"20257_CR274","doi-asserted-by":"crossref","unstructured":"Wu V, Manmatha R, Riseman EM (1997) Finding text in images. In: Proceedings of the 2nd ACM International Conference on Digital Libraries, pp. 3\u201312.","DOI":"10.1145\/263690.263766"},{"issue":"11","key":"20257_CR275","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/34.809116","volume":"21","author":"V Wu","year":"1999","unstructured":"Wu V, Manmatha R, Riseman EM (1999) Textfinder: An automatic system to detect and recognize text in images. IEEE Trans Pattern Anal Mach Intell 21(11):1224\u20131229","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR276","first-page":"1","volume":"2020","author":"W Wu","year":"2020","unstructured":"Wu W, Xing J, Yang C, Wang Y, Zhou H (2020) A scene text detector for text with arbitrary shapes. Math Probl Eng 2020:1\u201311","journal-title":"Math Probl Eng"},{"key":"20257_CR277","doi-asserted-by":"crossref","unstructured":"Xiao Y, Xue M, Lu T, Wu Y, Palaiahnakote S (2019) A text-context-aware CNN network for multi-oriented and multi-language scene text detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 695\u2013700.","DOI":"10.1109\/ICDAR.2019.00116"},{"key":"20257_CR278","doi-asserted-by":"crossref","unstructured":"Xu H, Su F (2015) A robust hierarchical detection method for scene text based on convolutional neural networks. In: 2015 IEEE International Conference on Multimedia and Expo (ICME) Jun 29 (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME.2015.7177494"},{"issue":"20","key":"20257_CR279","doi-asserted-by":"crossref","first-page":"11951","DOI":"10.1109\/JSEN.2020.2964939","volume":"20","author":"J Xu","year":"2020","unstructured":"Xu J, Ding W, Zhao H (2020) Based on improved edge detection algorithm for English text extraction and restoration from color images. IEEE Sens J 20(20):11951\u201311958","journal-title":"IEEE Sens J"},{"issue":"11","key":"20257_CR280","doi-asserted-by":"crossref","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","volume":"28","author":"Y Xu","year":"2019","unstructured":"Xu Y, Wang Y, Zhou W, Wang Y, Yang Z, Bai X (2019) Textfield: Learning a deep direction field for irregular scene text detection. IEEE Trans Image Process 28(11):5566\u20135579","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR281","doi-asserted-by":"crossref","unstructured":"Yadav V, Ragot N (2016) Text extraction in document images: highlight on using corner points. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), IEEE, pp. 281\u2013286.","DOI":"10.1109\/DAS.2016.67"},{"issue":"1","key":"20257_CR282","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1109\/TITS.2017.2749977","volume":"19","author":"C Yan","year":"2017","unstructured":"Yan C, Xie H, Liu S, Yin J, Zhang Y, Dai Q (2017) Effective Uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans Intell Transp Syst 19(1):220\u2013229","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"20257_CR283","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neucom.2012.12.070","volume":"134","author":"J Yan","year":"2014","unstructured":"Yan J, Gao X (2014) Detection and recognition of text superimposed in images base on layered method. Neurocomputing 134:3\u201314","journal-title":"Neurocomputing"},{"issue":"3","key":"20257_CR284","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1109\/TCYB.2014.2330657","volume":"45","author":"H Yang","year":"2015","unstructured":"Yang H, Wu S, Deng C, Lin W (2015) Scale and orientation invariant text segmentation for born-digital compound images. IEEE Transactions on Cybernetics 45(3):519\u2013533","journal-title":"IEEE Transactions on Cybernetics"},{"key":"20257_CR285","doi-asserted-by":"crossref","unstructured":"Yang L, Wang Q, Wang J, Quan X, Feng F, Chen Y, Khabsa M, Wang S, Xu Z, Liu D (2023) MixPAVE: Mix-prompt tuning for few-shot product attribute value extraction. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 9978\u20139991.","DOI":"10.18653\/v1\/2023.findings-acl.633"},{"key":"20257_CR286","doi-asserted-by":"crossref","first-page":"22588","DOI":"10.1109\/ACCESS.2019.2895330","volume":"7","author":"P Yang","year":"2019","unstructured":"Yang P, Zhang F, Yang G (2019) A fast scene text detector using knowledge distillation. IEEE Access 7:22588\u201322598","journal-title":"IEEE Access"},{"key":"20257_CR287","doi-asserted-by":"crossref","unstructured":"Yang X, Yumer E, Asente P, Kraley M, Kifer D, Lee Giles C (2017) Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5315\u20135324.","DOI":"10.1109\/CVPR.2017.462"},{"key":"20257_CR288","unstructured":"Yao C (2012) MSRA text detection 500 database (MSRA-TD500). Available at: http:\/\/www.iapr-tc11.org\/mediawiki\/index.php\/MSRA_Text_Detection_500_Database_(MSRA-TD500). Accessed 26 Oct 2012"},{"issue":"8","key":"20257_CR289","doi-asserted-by":"publisher","first-page":"e70173","DOI":"10.1371\/journal.pone.0070173","volume":"8","author":"C Yao","year":"2013","unstructured":"Yao C, Zhang X, Bai X, Liu W, Ma Y, Tu Z (2013) Rotation-invariant features for multi-oriented text detection in natural images. PLoS ONE 8(8):e70173. https:\/\/doi.org\/10.1371\/journal.pone.0070173","journal-title":"PLoS ONE"},{"key":"20257_CR290","unstructured":"Yao C, Bai X, Liu W, Ma Y, Tu Z (2012) Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 1083\u20131090."},{"issue":"11","key":"20257_CR291","doi-asserted-by":"crossref","first-page":"4737","DOI":"10.1109\/TIP.2014.2353813","volume":"23","author":"C Yao","year":"2014","unstructured":"Yao C, Bai X, Liu W (2014) A unified framework for multioriented text detection and recognition. IEEE Trans Image Process 23(11):4737\u20134749","journal-title":"IEEE Trans Image Process"},{"key":"20257_CR292","doi-asserted-by":"crossref","unstructured":"Yao JL, Wang YQ, Weng LB, Yang YP (2007) Locating text based on connected component and SVM. In: 2007 International Conference on Wavelet Analysis and Pattern Recognition, vol. 3. IEEE, pp. 1418\u20131423.","DOI":"10.1109\/ICWAPR.2007.4421657"},{"issue":"7","key":"20257_CR293","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye Q, Doermann D (2014) Text detection and recognition in imagery: A survey. IEEE Trans Pattern Anal Mach Intell 37(7):1480\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"20257_CR294","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.jvcir.2007.07.003","volume":"18","author":"Q Ye","year":"2007","unstructured":"Ye Q, Jiao J, Huang J, Yu H (2007) Text detection and restoration in natural scene images. J Vis Commun Image Represent 18(6):504\u2013513","journal-title":"J Vis Commun Image Represent"},{"key":"20257_CR295","doi-asserted-by":"crossref","unstructured":"Ye Q, Gao W, Wang W, Zeng W (2003) A robust text detection algorithm in images and video frames. In: Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint, vol. 2. IEEE, pp. 802\u2013806.","DOI":"10.1109\/ICICS.2003.1292567"},{"issue":"6","key":"20257_CR296","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1016\/j.imavis.2005.01.004","volume":"23","author":"Q Ye","year":"2005","unstructured":"Ye Q, Huang Q, Gao W, Zhao D (2005) Fast and robust text detection in images and video frames. Image Vis Comput 23(6):565\u2013576","journal-title":"Image Vis Comput"},{"issue":"9","key":"20257_CR297","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1109\/TIP.2011.2126586","volume":"20","author":"C Yi","year":"2011","unstructured":"Yi C, Tian Y (2011) Text string detection from natural scenes by structure-based partition and grouping. IEEE Trans Image Process 20(9):2594\u20132605","journal-title":"IEEE Trans Image Process"},{"issue":"9","key":"20257_CR298","doi-asserted-by":"crossref","first-page":"4256","DOI":"10.1109\/TIP.2012.2199327","volume":"21","author":"C Yi","year":"2012","unstructured":"Yi C, Tian Y (2012) Localizing text in scene images by boundary clustering, stroke segmentation, and string fragment classification. IEEE Trans Image Process 21(9):4256\u20134268","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"20257_CR299","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.cviu.2012.11.002","volume":"117","author":"C Yi","year":"2013","unstructured":"Yi C, Tian Y (2013) Text extraction from scene images by character appearance and structure modeling. Comput Vis Image Underst 117(2):182\u2013194","journal-title":"Comput Vis Image Underst"},{"issue":"5","key":"20257_CR300","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","volume":"36","author":"XC Yin","year":"2014","unstructured":"Yin XC, Yin X, Huang K, Hao HW (2014) Robust text detection in natural scene images. IEEE Trans Pattern Anal Mach Intell 36(5):970\u2013983","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"20257_CR301","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"XC Yin","year":"2015","unstructured":"Yin XC, Pei WY, Zhang J, Hao HW (2015) Multi-orientation scene text detection with adaptive clustering. IEEE Trans Pattern Anal Mach Intell 37(9):1930\u20131937","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"20257_CR302","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1049\/iet-cvi.2013.0307","volume":"9","author":"C Yu","year":"2015","unstructured":"Yu C, Song Y, Meng Q, Zhang Y, Liu Y (2015) Text detection and recognition in natural scene with edge analysis. IET Comput Vision 9(4):603\u2013613","journal-title":"IET Comput Vision"},{"key":"20257_CR303","doi-asserted-by":"crossref","unstructured":"Yuan Q, Tan CL (2001) Text extraction from gray scale document images using edge information. In: Proceedings of 6th International Conference on Document Analysis and Recognition, IEEE, pp. 302\u2013306.","DOI":"10.1109\/ICDAR.2001.953803"},{"key":"20257_CR304","first-page":"91","volume-title":"Asian conference on computer vision","author":"A Zamberletti","year":"2015","unstructured":"Zamberletti A, Noce L, Gallo I (2015) Text localization based on fast feature pyramids and multi-resolution maximally stable extremal regions. Asian conference on computer vision. Springer, Cham, pp 91\u2013105"},{"key":"20257_CR305","doi-asserted-by":"crossref","unstructured":"Zhan Y, Wang W, Gao W (2006) A robust split-and-merge text segmentation approach for images. In: 18th International Conference on Pattern Recognition (ICPR'06), vol. 2. IEEE, pp. 1002\u20131005.","DOI":"10.1109\/ICPR.2006.169"},{"key":"20257_CR306","first-page":"1","volume":"2020","author":"F Zhang","year":"2020","unstructured":"Zhang F, Luan J, Xu Z, Chen W (2020) DetReco: object-text detection and recognition based on deep neural network. Math Probl Eng 2020:1\u201315","journal-title":"Math Probl Eng"},{"key":"20257_CR307","doi-asserted-by":"crossref","unstructured":"Zhang H, Liu C, Yang C, Ding X, Wang K (2011) An improved scene text extraction method using conditional random field and optical character recognition. In: 2011 International Conference on Document Analysis and Recognition, IEEE, pp. 708\u2013712.","DOI":"10.1109\/ICDAR.2011.148"},{"key":"20257_CR308","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.neucom.2013.05.037","volume":"122","author":"H Zhang","year":"2013","unstructured":"Zhang H, Zhao K, Song YZ, Guo J (2013) Text extraction from natural scene image: a survey. Neurocomputing 122:310\u2013323","journal-title":"Neurocomputing"},{"key":"20257_CR309","unstructured":"Zhang J (2012) Extraction of text objects in image and video documents. Dissertation, University of South Florida."},{"key":"20257_CR310","doi-asserted-by":"crossref","unstructured":"Zhang J, Chong Y (2013) Text localization based on the Discrete Shearlet Transform. In: 2013 IEEE 4th International Conference on Software Engineering and Service Science, IEEE, pp. 262\u2013266.","DOI":"10.1109\/ICSESS.2013.6615301"},{"key":"20257_CR311","doi-asserted-by":"crossref","unstructured":"Zhang Q, Chen Y, Zhang Y, Xu Y (2008) SIFT implementation and optimization for multi-core systems. In: 2008 IEEE International Symposium on Parallel and Distributed Processing, IEEE, pp. 1\u20138.","DOI":"10.1109\/IPDPS.2008.4536131"},{"issue":"2","key":"20257_CR312","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1016\/j.ultrasmedbio.2014.09.003","volume":"41","author":"Q Zhang","year":"2015","unstructured":"Zhang Q, Xiao Y, Chen S, Wang C, Zheng H (2015) Quantification of elastic heterogeneity using contourlet-based texture analysis in shear-wave elastography for breast tumor classification. Ultrasound Med Biol 41(2):588\u2013600","journal-title":"Ultrasound Med Biol"},{"key":"20257_CR313","doi-asserted-by":"crossref","unstructured":"Zhang X, Sun F, Gu L (2010) A combined algorithm for video text extraction. In: 2010 7th International Conference on Fuzzy Systems and Knowledge Discovery, vol. 5. IEEE, pp. 2294\u20132298.","DOI":"10.1109\/FSKD.2010.5569311"},{"key":"20257_CR314","doi-asserted-by":"crossref","unstructured":"Zhang XW, Zheng XB, Weng ZJ (2008) Text extraction algorithm under background image using wavelet transforms. In: 2008 International Conference on Wavelet Analysis and Pattern Recognition, vol. 1. IEEE, pp. 200\u2013204.","DOI":"10.1109\/ICWAPR.2008.4635776"},{"key":"20257_CR315","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang C, Xiao B, Shi C (2012) A new text extraction method incorporating local information. In: 2012 International Conference on Frontiers in Handwriting Recognition, IEEE, pp. 252\u2013255.","DOI":"10.1109\/ICFHR.2012.164"},{"key":"20257_CR316","doi-asserted-by":"crossref","unstructured":"Zhang Z, Shen W, Yao C, Bai X (2015) Symmetry-based text line detection in natural scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2558\u20132567.","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"20257_CR317","doi-asserted-by":"crossref","unstructured":"Zhang Z, Zhang C, Shen W, Yao C, Liu W, Bai X (2016) Multi-oriented text detection with fully convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4159\u20134167.","DOI":"10.1109\/CVPR.2016.451"},{"issue":"15","key":"20257_CR318","doi-asserted-by":"crossref","first-page":"2431","DOI":"10.1016\/j.patrec.2005.04.014","volume":"26","author":"D Zheng","year":"2005","unstructured":"Zheng D, Zhao Y, Wang J (2005) An efficient method of license plate location. Pattern Recogn Lett 26(15):2431\u20132438","journal-title":"Pattern Recogn Lett"},{"issue":"2","key":"20257_CR319","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.jcss.2012.05.006","volume":"79","author":"L Zheng","year":"2013","unstructured":"Zheng L, He X, Samali B, Yang LT (2013) An algorithm for accuracy enhancement of license plate recognition. J Comput Syst Sci 79(2):245\u2013255","journal-title":"J Comput Syst Sci"},{"issue":"12","key":"20257_CR320","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1016\/j.imavis.2010.04.002","volume":"28","author":"M Zhao","year":"2010","unstructured":"Zhao M, Li S, Kwok J (2010) Text detection in images using sparse representation with discriminative dictionaries. Image Vis Comput 28(12):1590\u20131599","journal-title":"Image Vis Comput"},{"key":"20257_CR321","doi-asserted-by":"crossref","unstructured":"Zhao T, Sun G, Zhang C, Chen D (2008) Study on video text processing. In: 2008 IEEE International Symposium on Industrial Electronics, IEEE, pp. 1215\u20131218.","DOI":"10.1109\/ISIE.2008.4677025"},{"issue":"10","key":"20257_CR322","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1016\/0031-3203(95)00030-4","volume":"28","author":"Y Zhong","year":"1995","unstructured":"Zhong Y, Karu K, Jain AK (1995) Locating text in complex color images. Pattern Recogn 28(10):1523\u20131535","journal-title":"Pattern Recogn"},{"issue":"4","key":"20257_CR323","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1109\/34.845381","volume":"22","author":"Y Zhong","year":"2000","unstructured":"Zhong Y, Zhang H, Jain AK (2000) Automatic caption localization in compressed video. IEEE Trans Pattern Anal Mach Intell 22(4):385\u2013392","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20257_CR324","doi-asserted-by":"crossref","unstructured":"Zhou G, Liu Y, Meng Q, Zhang Y (2011) Detecting multilingual text in natural scene. In: 2011 1st International Symposium on Access Spaces (ISAS), IEEE, pp. 116\u2013120.","DOI":"10.1109\/ISAS.2011.5960931"},{"issue":"4","key":"20257_CR325","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1049\/iet-cvi.2014.0297","volume":"9","author":"G Zhou","year":"2015","unstructured":"Zhou G, Liu Y, Xu L, Jia Z (2015) Scene text detection method based on the hierarchical model. IET Comput Vision 9(4):500\u2013510","journal-title":"IET Comput Vision"},{"issue":"6","key":"20257_CR326","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1038\/s41551-023-01045-x","volume":"7","author":"HY Zhou","year":"2023","unstructured":"Zhou HY, Yu Y, Wang C, Zhang S, Gao Y, Pan J, Shao J, Lu G, Zhang K, Li W (2023) A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nat Biomed Eng 7(6):743\u2013755","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"20257_CR327","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu Y, Yao C, Bai X (2016) Scene text detection and recognition: Recent advances and future trends. Front Comp Sci 10(1):19\u201336","journal-title":"Front Comp Sci"},{"issue":"1","key":"20257_CR328","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TITS.2017.2768827","volume":"19","author":"Y Zhu","year":"2018","unstructured":"Zhu Y, Liao M, Yang M, Liu W (2018) Cascaded segmentation-detection networks for text-based traffic sign detection. IEEE Trans Intell Transp Syst 19(1):209\u2013219","journal-title":"IEEE Trans Intell Transp Syst"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20257-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20257-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20257-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T21:36:18Z","timestamp":1739309778000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20257-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":328,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["20257"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20257-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"17 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"In this review article, no experimentation is performed on animals or any human beings. This review article does not affect the environment as well.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"There is no conflict of interest at any stage.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}