{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T01:19:53Z","timestamp":1781659193896,"version":"3.54.5"},"reference-count":268,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":["Artif Intell Rev"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s10462-023-10530-3","type":"journal-article","created":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T12:01:45Z","timestamp":1687089705000},"page":"15301-15373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Scene text understanding: recapitulating the past decade"],"prefix":"10.1007","volume":"56","author":[{"given":"Mridul","family":"Ghosh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Himadri","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sk Md","family":"Obaidullah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Zhi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3360-7576","authenticated-orcid":false,"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,18]]},"reference":[{"key":"10530_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam A, Litman R, Tsiper S, Anschel O, Slossberg R, Mazor S, Manmatha R, Perona P (2021) Sequence-to-sequence contrastive learning for text recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15302\u201315312","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"10530_CR2","doi-asserted-by":"crossref","unstructured":"Afzal MZ, Pastor-Pellicer J, Shafait F, Breuel TM, Dengel A, Liwicki M (2015) Document image binarization using lstm: a sequence learning approach. In: Proceedings of the 3rd international workshop on historical document imaging and processing, pp 79\u201384","DOI":"10.1145\/2809544.2809561"},{"issue":"4","key":"10530_CR3","first-page":"1083","volume":"2","author":"P Agrawal","year":"2012","unstructured":"Agrawal P, Varma R (2012) Text extraction from images. IJCSET 2(4):1083\u20131087","journal-title":"IJCSET"},{"key":"10530_CR4","doi-asserted-by":"crossref","unstructured":"Akata Z, Perronnin F, Harchaoui Z, Schmid C (2013) Label-embedding for attribute-based classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 819\u2013826","DOI":"10.1109\/CVPR.2013.111"},{"key":"10530_CR5","unstructured":"Ammirato P, Berg AC (2019) A mask-rcnn baseline for probabilistic object detection. arXiv:1908.03621"},{"key":"10530_CR6","doi-asserted-by":"crossref","unstructured":"Angadi S, Kodabagi M (2010) Text region extraction from low resolution natural scene images using texture features. In: 2010 IEEE 2nd international advance computing conference (IACC). IEEE, pp 121\u2013128","DOI":"10.1109\/IADCC.2010.5423026"},{"key":"10530_CR7","doi-asserted-by":"crossref","unstructured":"Atienza R (2021a) Data augmentation for scene text recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1561\u20131570","DOI":"10.1109\/ICCVW54120.2021.00181"},{"key":"10530_CR8","doi-asserted-by":"crossref","unstructured":"Atienza R (2021b) Vision transformer for fast and efficient scene text recognition. In: International conference on document analysis and recognition. Springer, New York, pp 319\u2013334","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"10530_CR9","doi-asserted-by":"crossref","unstructured":"Azadboni MK, Samadhiya A, Khatri P (2014) Multi-orientation text detection by skeletonization (motds). In: 2014 2nd international symposium on computational and business intelligence. IEEE, pp 5\u20139","DOI":"10.1109\/ISCBI.2014.9"},{"key":"10530_CR10","doi-asserted-by":"crossref","unstructured":"Baek J, Kim G, Lee J, Park S, Han D, Yun S, Oh SJ, Lee H (2019) What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4715\u20134723","DOI":"10.1109\/ICCV.2019.00481"},{"key":"10530_CR11","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":"10530_CR12","doi-asserted-by":"crossref","unstructured":"Bai F, Cheng Z, Niu Y, Pu S, Zhou S (2018) Edit probability for scene text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1508\u20131516","DOI":"10.1109\/CVPR.2018.00163"},{"key":"10530_CR13","doi-asserted-by":"crossref","unstructured":"Bhattacharyya S, Kumar J, Ghoshal K (2020) Mathematical modeling and computational tools: ICACM 2018, Kharagpur, India, November 23\u201325, vol 320. Springer, New York","DOI":"10.1007\/978-981-15-3615-1"},{"key":"10530_CR14","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.patcog.2018.07.034","volume":"85","author":"AK Bhunia","year":"2019","unstructured":"Bhunia AK, Konwer A, Bhunia AK, Bhowmick A, Roy PP, Pal U (2019) Script identification in natural scene image and video frames using an attention based convolutional-lstm network. Pattern Recogn 85:172\u2013184","journal-title":"Pattern Recogn"},{"key":"10530_CR15","doi-asserted-by":"crossref","unstructured":"Bissacco A, Cummins M, Netzer Y, Neven H (2013) Photoocr: reading text in uncontrolled conditions. In: Proceedings of the Ieee international conference on computer vision, pp 785\u2013792","DOI":"10.1109\/ICCV.2013.102"},{"key":"10530_CR16","doi-asserted-by":"crossref","unstructured":"Borisyuk F, Gordo A, Sivakumar V (2018) Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 71\u201379","DOI":"10.1145\/3219819.3219861"},{"key":"10530_CR17","doi-asserted-by":"crossref","unstructured":"Boureau Y-L, Bach F, LeCun Y, Ponce J (2010) Learning mid-level features for recognition. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 2559\u20132566","DOI":"10.1109\/CVPR.2010.5539963"},{"key":"10530_CR18","doi-asserted-by":"crossref","unstructured":"Busta M, Neumann L, Matas J (2017) Deep textspotter: an end-to-end trainable scene text localization and recognition framework. In: Proceedings of the IEEE international conference on computer vision, pp 2204\u20132212","DOI":"10.1109\/ICCV.2017.242"},{"key":"10530_CR19","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.patcog.2018.08.011","volume":"86","author":"J Calvo-Zaragoza","year":"2019","unstructured":"Calvo-Zaragoza J, Gallego A-J (2019) A selectional auto-encoder approach for document image binarization. Pattern Recogn 86:37\u201347","journal-title":"Pattern Recogn"},{"key":"10530_CR20","doi-asserted-by":"crossref","first-page":"155441","DOI":"10.1109\/ACCESS.2020.3018784","volume":"8","author":"Y Cao","year":"2020","unstructured":"Cao Y, Ma S, Pan H (2020) Fdta: fully convolutional scene text detection with text attention. IEEE Access 8:155441\u2013155449","journal-title":"IEEE Access"},{"issue":"3","key":"10530_CR21","doi-asserted-by":"crossref","first-page":"486","DOI":"10.3390\/sym13030486","volume":"13","author":"D Cao","year":"2021","unstructured":"Cao D, Dang J, Zhong Y (2021) Towards accurate scene text detection with bidirectional feature pyramid network. Symmetry 13(3):486","journal-title":"Symmetry"},{"key":"10530_CR28","unstructured":"Chen X, Yuille AL (2004) Detecting and reading text in natural scenes. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition. CVPR 2004, vol. 2. IEEE"},{"key":"10530_CR27","doi-asserted-by":"crossref","unstructured":"Chen H, Tsai SS, Schroth G, Chen DM, Grzeszczuk R, Girod B (2011) Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: 2011 18th IEEE international conference on image processing. IEEE, pp 2609\u20132612","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"10530_CR26","unstructured":"Chen J, Ma T, Xiao C (2018) Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv:1801.10247"},{"issue":"2","key":"10530_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3440756","volume":"54","author":"X Chen","year":"2021","unstructured":"Chen X, Jin L, Zhu Y, Luo C, Wang T (2021) Text recognition in the wild: a survey. ACM Comput Surv (CSUR) 54(2):1\u201335","journal-title":"ACM Comput Surv (CSUR)"},{"key":"10530_CR23","doi-asserted-by":"crossref","unstructured":"Cheng Z, Bai F, Xu Y, Zheng G, Pu S, Zhou S (2017) Focusing attention: towards accurate text recognition in natural images. In: Proceedings of the IEEE international conference on computer vision, pp 5076\u20135084","DOI":"10.1109\/ICCV.2017.543"},{"key":"10530_CR25","doi-asserted-by":"crossref","unstructured":"Cheng Z, Xu Y, Bai F, Niu Y, Pu S, Zhou S (2018) Aon: towards arbitrarily-oriented text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5571\u20135579","DOI":"10.1109\/CVPR.2018.00584"},{"key":"10530_CR24","doi-asserted-by":"crossref","unstructured":"Cheng C, Huang Q, Bai X, Feng B, Liu W (2019) Patch aggregator for scene text script identification. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, pp 1077\u20131083","DOI":"10.1109\/ICDAR.2019.00175"},{"key":"10530_CR29","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng CK, Chan CS (2017) Total-text: a comprehensive dataset for scene text detection and recognition. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 935\u2013942","DOI":"10.1109\/ICDAR.2017.157"},{"key":"10530_CR30","doi-asserted-by":"crossref","unstructured":"Chng CK, Liu Y, Sun Y, Ng CC, Luo C, Ni Z, Fang C, Zhang S, Han J, Ding E, et al (2019) Icdar2019 robust reading challenge on arbitrary-shaped text-rrc-art. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, pp 1571\u20131576","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"10530_CR31","doi-asserted-by":"crossref","unstructured":"Chowdhury AR, Bhattacharya U, Parui SK (2011) Text detection of two major Indian scripts in natural scene images. In: International workshop on camera-based document analysis and recognition. Springer, New York, pp 42\u201357","DOI":"10.1007\/978-3-642-29364-1_4"},{"key":"10530_CR32","doi-asserted-by":"crossref","unstructured":"Coates A, Carpenter B, Case C, Satheesh S, Suresh B, Wang T, Wu DJ, Ng AY (2011) Text detection and character recognition in scene images with unsupervised feature learning. In: 2011 international conference on document analysis and recognition. IEEE, pp 440\u2013445","DOI":"10.1109\/ICDAR.2011.95"},{"key":"10530_CR33","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), vol 1, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"10530_CR34","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.procs.2012.09.126","volume":"13","author":"M Darab","year":"2012","unstructured":"Darab M, Rahmati M (2012) A hybrid approach to localize farsi text in natural scene images. Procedia Comput. Sci. 13:171\u2013184","journal-title":"Procedia Comput. Sci."},{"issue":"4","key":"10530_CR35","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","volume":"27","author":"S Dargan","year":"2020","unstructured":"Dargan S, Kumar M, Ayyagari MR, Kumar G (2020) A survey of deep learning and its applications: a new paradigm to machine learning. Arch. Comput. Methods Eng. 27(4):1071\u20131092","journal-title":"Arch. Comput. Methods Eng."},{"key":"10530_CR36","doi-asserted-by":"crossref","unstructured":"Dasgupta K, Das S, Bhattacharya U (2020) Scale-invariant multi-oriented text detection in wild scene image. In: 2020 IEEE international conference on image processing (ICIP), pp 2041\u20132045. IEEE","DOI":"10.1109\/ICIP40778.2020.9191102"},{"key":"10530_CR37","unstructured":"Dauphin YN, Fan A, Auli M, Grangier D (2017) Language modeling with gated convolutional networks. In: International conference on machine learning. PMLR, pp 933\u2013941"},{"key":"10530_CR38","first-page":"1","volume":"7","author":"TE De Campos","year":"2009","unstructured":"De Campos TE, Babu BR, Varma M et al (2009) Character recognition in natural images. VISAPP 7:1\u201310","journal-title":"VISAPP"},{"key":"10530_CR39","doi-asserted-by":"crossref","unstructured":"Decker LGL, Pinto A, Campana JLF, Neira MC, dos Santos AA, Concei\u00e7ao JS, Angeloni MA, Li LT, et al (2020) MobText: a compact method for scene text localization. VISAPP","DOI":"10.5220\/0008954103430350"},{"key":"10530_CR40","doi-asserted-by":"crossref","unstructured":"Del\u00a0Gobbo J, Herrera RM (2020) Unconstrained text detection in manga: a new dataset and baseline. In: European conference on computer vision. Springer, New York, pp 629\u2013646","DOI":"10.1007\/978-3-030-67070-2_38"},{"key":"10530_CR41","doi-asserted-by":"crossref","unstructured":"Deng D, Liu H, Li X, Cai D (2018) Pixellink: detecting scene text via instance segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"10530_CR42","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.neucom.2017.02.061","volume":"242","author":"S Dey","year":"2017","unstructured":"Dey S, Shivakumara P, Raghunandan K, Pal U, Lu T, Kumar GH, Chan CS (2017) Script independent approach for multi-oriented text detection in scene image. Neurocomputing 242:96\u2013112","journal-title":"Neurocomputing"},{"issue":"3","key":"10530_CR44","doi-asserted-by":"crossref","first-page":"31","DOI":"10.4018\/IJCVIP.2020070103","volume":"10","author":"D Dhar","year":"2020","unstructured":"Dhar D, Chakraborty N, Choudhury S, Paul A, Mollah AF, Basu S, Sarkar R (2020) Multilingual scene text detection using gradient morphology. Int J Comput Vis Image Process (IJCVIP) 10(3):31\u201343","journal-title":"Int J Comput Vis Image Process (IJCVIP)"},{"key":"10530_CR45","doi-asserted-by":"crossref","unstructured":"Dizaji KG, Zheng F, Sadoughi N, Yang Y, Deng C, Huang H (2018) Unsupervised deep generative adversarial hashing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3664\u20133673","DOI":"10.1109\/CVPR.2018.00386"},{"key":"10530_CR46","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. IEEE, pp 2963\u20132970","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"10530_CR47","doi-asserted-by":"crossref","unstructured":"Fang S, Xie H, Zha Z-J, Sun N, Tan J, Zhang Y (2018) Attention and language ensemble for scene text recognition with convolutional sequence modeling. In: Proceedings of the 26th ACM international conference on multimedia, pp 248\u2013256","DOI":"10.1145\/3240508.3240571"},{"key":"10530_CR49","doi-asserted-by":"crossref","unstructured":"Fasil O, Manjunath S, Aradhya VM (2017) Word-level script identification from scene images. In: Proceedings of the 5th international conference on frontiers in intelligent computing: theory and applications. Springer, New York, pp 417\u2013426","DOI":"10.1007\/978-981-10-3156-4_43"},{"key":"10530_CR50","doi-asserted-by":"crossref","unstructured":"Feng Y, Song Y, Zhang Y (2016) Scene text detection based on multi-scale swt and edge filtering. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp 645\u2013650","DOI":"10.1109\/ICPR.2016.7899707"},{"issue":"3","key":"10530_CR51","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1007\/s11263-014-0700-1","volume":"108","author":"B Fernando","year":"2014","unstructured":"Fernando B, Fromont E, Tuytelaars T (2014) Mining mid-level features for image classification. Int J Comput Vision 108(3):186\u2013203","journal-title":"Int J Comput Vision"},{"key":"10530_CR52","unstructured":"Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning. PMLR, pp 1180\u20131189"},{"key":"10530_CR53","doi-asserted-by":"crossref","unstructured":"Gao H, Li Y, Wang X, Han J, Li R (2019) Ensemble attention for text recognition in natural images. In: 2019 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN.2019.8852010"},{"key":"10530_CR54","doi-asserted-by":"crossref","unstructured":"Gao D, Li K, Wang R, Shan S, Chen X (2020) Multi-modal graph neural network for joint reasoning on vision and scene text. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12746\u201312756","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"10530_CR55","doi-asserted-by":"crossref","unstructured":"Garcia C, Apostolidis X (2000) Text detection and segmentation in complex color images. In: 2000 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 00CH37100), vol. 4. IEEE, pp 2326\u20132329","DOI":"10.1109\/ICASSP.2000.859306"},{"key":"10530_CR63","doi-asserted-by":"crossref","unstructured":"Ghosh M, Obaidullah SM, Santosh K, Das N, Roy K (2018) Artistic multi-character script identification using iterative isotropic dilation algorithm. In: International conference on recent trends in image processing and pattern recognition. Springer, New York, pp 49\u201362","DOI":"10.1007\/978-981-13-9187-3_5"},{"key":"10530_CR61","doi-asserted-by":"crossref","unstructured":"Ghosh M, Mukherjee H, Obaidullah SM, Santosh K, Das N, Roy K (2019a) Artistic multi-character script identification. In: Document processing using machine learning. Chapman and Hall\/CRC, Boston, pp 28\u201342","DOI":"10.1201\/9780429277573-3"},{"key":"10530_CR62","doi-asserted-by":"crossref","unstructured":"Ghosh M, Mukherjee H, Obaidullah SM, Santosh K, Das N, Roy K (2019b) Identifying the presence of graphical texts in scene images using cnn. In: 2019 international conference on document analysis and recognition workshops (ICDARW), vol 1. IEEE, pp 86\u201391","DOI":"10.1109\/ICDARW.2019.00020"},{"key":"10530_CR64","doi-asserted-by":"crossref","unstructured":"Ghosh M, Roy SS, Mukherjee H, Obaidullah SM, Santosh K, Roy K (2019c) Automatic text localization in scene images: a transfer learning based approach. In: National conference on computer vision, pattern recognition, image processing, and graphics. Springer, New York, pp 470\u2013479","DOI":"10.1007\/978-981-15-8697-2_44"},{"key":"10530_CR56","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1016\/j.procs.2020.03.268","volume":"167","author":"M Ghosh","year":"2020","unstructured":"Ghosh M, Mukherjee H, Obaidullah SM, Santosh K, Das N, Roy K (2020) Artistic multi-script identification at character level with extreme learning machine. Procedia Comput. Sci. 167:496\u2013505","journal-title":"Procedia Comput. Sci."},{"key":"10530_CR57","first-page":"1","volume":"1","author":"M Ghosh","year":"2021","unstructured":"Ghosh M, Mukherjee H, Obaidullah SM, Santosh K, Das N, Roy K (2021a) Lwsinet: a deep learning-based approach towards video script identification. Multimed Tools Appl 1:1\u201334","journal-title":"Multimed Tools Appl"},{"key":"10530_CR58","doi-asserted-by":"crossref","first-page":"125184","DOI":"10.1109\/ACCESS.2021.3110858","volume":"9","author":"M Ghosh","year":"2021","unstructured":"Ghosh M, Roy SS, Mukherjee H, Obaidullah SM, Gao X-Z, Roy K (2021b) Movie title extraction and script separation using shallow convolution neural network. IEEE Access 9:125184\u2013125201","journal-title":"IEEE Access"},{"issue":"5","key":"10530_CR59","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1007\/s00371-021-02094-6","volume":"38","author":"M Ghosh","year":"2022","unstructured":"Ghosh M, Roy SS, Mukherjee H, Obaidullah SM, Santosh K, Roy K (2022) Understanding movie poster: transfer-deep learning approach for graphic-rich text recognition. Vis Comput 38(5):1645\u20131664","journal-title":"Vis Comput"},{"key":"10530_CR60","doi-asserted-by":"crossref","unstructured":"Ghoshal R, Banerjee A (2020) Svm and mlp based segmentation and recognition of text from scene images through an effective binarization scheme. In: Computational intelligence in pattern recognition. Springer, New York, pp 237\u2013246","DOI":"10.1007\/978-981-13-9042-5_20"},{"key":"10530_CR65","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"10530_CR66","doi-asserted-by":"crossref","unstructured":"Gkioxari G, Girshick R, Malik J (2015) Contextual action recognition with r* cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1080\u20131088","DOI":"10.1109\/ICCV.2015.129"},{"key":"10530_CR67","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"},{"key":"10530_CR68","doi-asserted-by":"crossref","unstructured":"Gllavata J, Freisleben B (2005) Script recognition in images with complex backgrounds. In: Proceedings of the fifth IEEE international symposium on signal processing and information technology, 2005. IEEE, pp 589\u2013594","DOI":"10.1109\/ISSPIT.2005.1577163"},{"key":"10530_CR69","doi-asserted-by":"crossref","unstructured":"Goel V, Mishra A, Alahari K, Jawahar C (2013) Whole is greater than sum of parts: Recognizing scene text words. In: 2013 12th international conference on document analysis and recognition. IEEE, pp 398\u2013402","DOI":"10.1109\/ICDAR.2013.87"},{"key":"10530_CR72","doi-asserted-by":"crossref","unstructured":"Gomez L, Karatzas D (2013) Multi-script text extraction from natural scenes. In: 2013 12th international conference on document analysis and recognition. IEEE, pp 467\u2013471","DOI":"10.1109\/ICDAR.2013.100"},{"key":"10530_CR73","doi-asserted-by":"crossref","unstructured":"Gomez L, Karatzas D (2016) A fine-grained approach to scene text script identification. In: 2016 12th IAPR workshop on document analysis systems (DAS). IEEE, pp 192\u2013197","DOI":"10.1109\/DAS.2016.64"},{"key":"10530_CR70","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.patcog.2017.01.032","volume":"67","author":"L Gomez","year":"2017","unstructured":"Gomez L, Nicolaou A, Karatzas D (2017) Improving patch-based scene text script identification with ensembles of conjoined networks. Pattern Recogn 67:85\u201396","journal-title":"Pattern Recogn"},{"key":"10530_CR74","unstructured":"Gonzalez A, Bergasa LM, Yebes JJ, Bronte S (2012) Text location in complex images. In: Proceedings of the 21st international conference on pattern recognition (ICPR2012). IEEE, pp 617\u2013620"},{"key":"10530_CR75","unstructured":"Goodfellow IJ, Bulatov Y, Ibarz J, Arnoud S, Shet V (2013a) Multi-digit number recognition from street view imagery using deep convolutional neural networks. arXiv:1312.6082"},{"key":"10530_CR77","unstructured":"Goodfellow I, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013b) Maxout networks. In: International conference on machine learning. PMLR, pp 1319\u20131327"},{"key":"10530_CR76","first-page":"1","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. Adv Neural Inf Process Syst 27:1\u201310","journal-title":"Adv Neural Inf Process Syst"},{"key":"10530_CR78","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, pp 2315\u20132324","DOI":"10.1109\/CVPR.2016.254"},{"issue":"6","key":"10530_CR79","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 (2016a) Text-attentional convolutional neural network for scene text detection. IEEE Trans Image Process 25(6):2529\u20132541","journal-title":"IEEE Trans Image Process"},{"key":"10530_CR82","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016b) Deep residual learning for image recognition. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10530_CR81","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"issue":"11","key":"10530_CR80","doi-asserted-by":"crossref","first-page":"5406","DOI":"10.1109\/TIP.2018.2855399","volume":"27","author":"W He","year":"2018","unstructured":"He W, Zhang X-Y, Yin F, Liu C-L (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":"10530_CR83","doi-asserted-by":"crossref","unstructured":"Howe NR (2011) A Laplacian energy for document binarization. In: 2011 international conference on document analysis and recognition. IEEE, pp 6\u201310","DOI":"10.1109\/ICDAR.2011.11"},{"key":"10530_CR89","doi-asserted-by":"crossref","unstructured":"Hu Z, Pi P, Wu Z, Xue Y, Shen J, Tan J, Lian X, Wang Z, Liu J (2021) E2vts: energy-efficient video text spotting from unmanned aerial vehicles. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 905\u2013913","DOI":"10.1109\/CVPRW53098.2021.00101"},{"key":"10530_CR84","doi-asserted-by":"crossref","unstructured":"Huang W, Lin Z, Yang J, Wang J (2013a) 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":"10530_CR87","doi-asserted-by":"crossref","unstructured":"Huang R, Shivakumara P, Uchida S (2013b) Scene character detection by an edge-ray filter. In: 2013 12th international conference on document analysis and recognition. IEEE, pp 462\u2013466","DOI":"10.1109\/ICDAR.2013.99"},{"key":"10530_CR86","doi-asserted-by":"crossref","unstructured":"Huang W, Qiao Y, Tang X (2014) Robust scene text detection with convolution neural network induced mser trees. In: European conference on computer vision. Springer, New York, pp 497\u2013511","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"10530_CR88","doi-asserted-by":"crossref","unstructured":"Huang Z, Zhong Z, Sun L, Huo Q (2019) Mask r-cnn with pyramid attention network for scene text detection. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 764\u2013772","DOI":"10.1109\/WACV.2019.00086"},{"key":"10530_CR85","doi-asserted-by":"crossref","unstructured":"Huang J, Pang G, Kovvuri R, Toh M, Liang KJ, Krishnan P, Yin X, Hassner T (2021) A multiplexed network for end-to-end, multilingual ocr. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4547\u20134557","DOI":"10.1109\/CVPR46437.2021.00452"},{"key":"10530_CR91","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014a) Synthetic data and artificial neural networks for natural scene text recognition. arXiv:1406.2227"},{"key":"10530_CR92","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014b) Deep features for text spotting. In: European conference on computer vision. Springer, New York, pp 512\u2013528","DOI":"10.1007\/978-3-319-10593-2_34"},{"issue":"1","key":"10530_CR90","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 Vis 116(1):1\u201320","journal-title":"Int J Comput Vis"},{"key":"10530_CR94","doi-asserted-by":"crossref","unstructured":"Jang I, Ko B, Byun H, Choi Y (2002) Automatic text extraction in news images using morphology. In: Visual communications and image processing 2002, vol 4671. International Society for Optics and Photonics, pp 521\u2013530","DOI":"10.1117\/12.453094"},{"key":"10530_CR95","doi-asserted-by":"crossref","unstructured":"Juneja M, Vedaldi A, Jawahar C, Zisserman A (2013) Blocks that shout: distinctive parts for scene classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 923\u2013930","DOI":"10.1109\/CVPR.2013.124"},{"key":"10530_CR98","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, Iwamura M, Bigorda LG, Mestre SR, Mas J, Mota DF, Almazan JA, De\u00a0Las\u00a0Heras 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":"10530_CR96","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S, Bagdanov A, Iwamura M, Matas J, Neumann L, Chandrasekhar VR, Lu S, et al (2015) Icdar 2015 competition on robust reading. In: 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10530_CR99","doi-asserted-by":"crossref","unstructured":"Kasar T, Ramakrishnan AG (2011) Multi-script and multi-oriented text localization from scene images. In: International workshop on camera-based document analysis and recognition. Springer, New York, pp 1\u201314","DOI":"10.1007\/978-3-642-29364-1_1"},{"key":"10530_CR100","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2021.107043","volume":"91","author":"A Khalil","year":"2021","unstructured":"Khalil A, Jarrah M, Al-Ayyoub M, Jararweh Y (2021) Text detection and script identification in natural scene images using deep learning. Comput. Electr. Eng. 91:107043","journal-title":"Comput. Electr. Eng."},{"issue":"22","key":"10530_CR101","doi-asserted-by":"crossref","first-page":"32159","DOI":"10.1007\/s11042-019-08028-8","volume":"78","author":"T Khan","year":"2019","unstructured":"Khan T, Mollah AF (2019) Autnt-a component level dataset for text non-text classification and benchmarking with novel script invariant feature descriptors and d-cnn. Multimed Tools Appl 78(22):32159\u201332186","journal-title":"Multimed Tools Appl"},{"issue":"5","key":"10530_CR102","doi-asserted-by":"crossref","first-page":"3239","DOI":"10.1007\/s10462-020-09930-6","volume":"54","author":"T Khan","year":"2021","unstructured":"Khan T, Sarkar R, Mollah AF (2021) Deep learning approaches to scene text detection: a comprehensive review. Artif Intell Rev 54(5):3239\u20133298","journal-title":"Artif Intell Rev"},{"issue":"12","key":"10530_CR104","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"},{"key":"10530_CR103","unstructured":"Kim K-H, Hong S, Roh B, Cheon Y, Park M (2016) Pvanet: deep but lightweight neural networks for real-time object detection. arXiv:1608.08021"},{"key":"10530_CR105","doi-asserted-by":"crossref","unstructured":"Kim S, Hori T, Watanabe S (2017) Joint ctc-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4835\u20134839","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"10530_CR106","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"10530_CR107","doi-asserted-by":"crossref","unstructured":"Kong H, Tang D, Meng X, Lu T (2019) Garn: a novel generative adversarial recognition network for end-to-end scene character recognition. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, pp 689\u2013694","DOI":"10.1109\/ICDAR.2019.00115"},{"key":"10530_CR108","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"10530_CR109","doi-asserted-by":"crossref","unstructured":"Kumuda T, Basavaraj L (2015) Detection and localization of text from natural scene images using texture features. In: 2015 IEEE international conference on computational intelligence and computing research (ICCIC). IEEE, pp 1\u20134","DOI":"10.1109\/ICCIC.2015.7435688"},{"key":"10530_CR111","doi-asserted-by":"crossref","unstructured":"Lee C-Y, Bhardwaj A, Di W, Jagadeesh V, Piramuthu R (2014) Region-based discriminative feature pooling for scene text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4050\u20134057","DOI":"10.1109\/CVPR.2014.516"},{"key":"10530_CR110","doi-asserted-by":"crossref","unstructured":"Lee CY, Baek Y, Lee H (2019) Tedeval: a fair evaluation metric for scene text detectors. In: 2019 international conference on document analysis and recognition workshops (ICDARW), vol 7. IEEE, pp 14\u201317","DOI":"10.1109\/ICDARW.2019.60125"},{"issue":"5","key":"10530_CR113","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1007\/s00138-018-0942-y","volume":"29","author":"Z Lei","year":"2018","unstructured":"Lei Z, Zhao S, Song H, Shen J (2018) Scene text recognition using residual convolutional recurrent neural network. Mach Vis Appl 29(5):861\u2013871","journal-title":"Mach Vis Appl"},{"issue":"1","key":"10530_CR114","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":"10530_CR126","doi-asserted-by":"crossref","unstructured":"Li H, Wang P, Shen C (2017) Towards end-to-end text spotting with convolutional recurrent neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 5238\u20135246","DOI":"10.1109\/ICCV.2017.560"},{"key":"10530_CR127","doi-asserted-by":"crossref","unstructured":"Li H, Wang P, Shen C, Zhang G (2019a) Show, attend and read: a simple and strong baseline for irregular text recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8610\u20138617","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"10530_CR128","doi-asserted-by":"crossref","unstructured":"Li K, Zhang Y, Li K, Li Y, Fu Y (2019b) Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4654\u20134662","DOI":"10.1109\/ICCV.2019.00475"},{"key":"10530_CR115","doi-asserted-by":"crossref","unstructured":"Liao M, Zhang J, Wan Z, Xie F, Liang J, Lyu P, Yao C, Bai X (2019) Scene text recognition from two-dimensional perspective. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8714\u20138721","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"10530_CR116","doi-asserted-by":"crossref","unstructured":"Lim JJ, Zitnick CL, Doll\u00e1r P (2013) Sketch tokens: A learned mid-level representation for contour and object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3158\u20133165","DOI":"10.1109\/CVPR.2013.406"},{"key":"10530_CR118","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) Refinenet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1925\u20131934","DOI":"10.1109\/CVPR.2017.549"},{"issue":"2","key":"10530_CR117","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1007\/s11831-019-09315-1","volume":"27","author":"H Lin","year":"2020","unstructured":"Lin H, Yang P, Zhang F (2020) Review of scene text detection and recognition. Arch Comput Methods Eng 27(2):433\u2013454","journal-title":"Arch Comput Methods Eng"},{"key":"10530_CR121","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016a) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, New York, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10530_CR122","doi-asserted-by":"crossref","unstructured":"Liu W, Chen C, Wong K-YK, Su Z, Han J (2016b) Star-net: a spatial attention residue network for scene text recognition. In: BMVC, vol 2, p 7","DOI":"10.5244\/C.30.43"},{"key":"10530_CR124","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin G, Yang S, Feng J, Lin W, Goh WL (2018a) Learning markov clustering networks for scene text detection. arXiv:1805.08365","DOI":"10.1109\/CVPR.2018.00725"},{"key":"10530_CR125","doi-asserted-by":"crossref","unstructured":"Liu Z, Li Y, Ren F, Goh WL, Yu H (2018b) Squeezedtext: a real-time scene text recognition by binary convolutional encoder-decoder network. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12252"},{"issue":"2","key":"10530_CR119","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s10032-019-00320-5","volume":"22","author":"X Liu","year":"2019","unstructured":"Liu X, Meng G, Pan C (2019) Scene text detection and recognition with advances in deep learning: a survey. Int J Doc Anal Recogn (IJDAR) 22(2):143\u2013162","journal-title":"Int J Doc Anal Recogn (IJDAR)"},{"key":"10530_CR123","unstructured":"Liu H, Guo A, Jiang D, Hu Y, Ren B (2020) Puzzlenet: scene text detection by segment context graph learning. arXiv:2002.11371"},{"issue":"6","key":"10530_CR120","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1007\/s11263-021-01459-7","volume":"129","author":"Y Liu","year":"2021","unstructured":"Liu Y, He T, Chen H, Wang X, Luo C, Zhang S, Shen C, Jin L (2021) Exploring the capacity of an orderless box discretization network for multi-orientation scene text detection. Int J Comput Vis 129(6):1972\u20131992","journal-title":"Int J Comput Vis"},{"issue":"1","key":"10530_CR129","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long S, He X, Yao C (2021) Scene text detection and recognition: the deep learning era. Int J Comput Vis 129(1):161\u2013184","journal-title":"Int J Comput Vis"},{"key":"10530_CR130","unstructured":"Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning. PMLR, pp 97\u2013105"},{"key":"10530_CR131","doi-asserted-by":"crossref","unstructured":"Long S, Ruan J, Zhang W, He X, Wu W, Yao C (2018) Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European conference on computer vision (ECCV), pp 20\u201336","DOI":"10.1007\/978-3-030-01216-8_2"},{"issue":"4","key":"10530_CR132","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10032-010-0130-8","volume":"13","author":"S Lu","year":"2010","unstructured":"Lu S, Su B, Tan CL (2010) Document image binarization using background estimation and stroke edges. Int J Doc Anal Recogn (IJDAR) 13(4):303\u2013314","journal-title":"Int J Doc Anal Recogn (IJDAR)"},{"key":"10530_CR133","doi-asserted-by":"crossref","first-page":"52669","DOI":"10.1109\/ACCESS.2019.2911964","volume":"7","author":"L Lu","year":"2019","unstructured":"Lu L, Yi Y, Huang F, Wang K, Wang Q (2019) Integrating local CNN and global CNN for script identification in natural scene images. IEEE Access 7:52669\u201352679","journal-title":"IEEE Access"},{"key":"10530_CR134","doi-asserted-by":"crossref","unstructured":"Lucas SM (2005) Icdar 2005 text locating competition results. In: Eighth international conference on document analysis and recognition (ICDAR\u201905), pp 80\u201384","DOI":"10.1109\/ICDAR.2005.231"},{"issue":"2\u20133","key":"10530_CR135","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","volume":"7","author":"SM Lucas","year":"2005","unstructured":"Lucas SM, Panaretos A, Sosa L, Tang A, Wong S, Young R, Ashida K, Nagai H, Okamoto M, Yamamoto H et al (2005) Icdar 2003 robust reading competitions: entries, results, and future directions. IJDAR 7(2\u20133):105\u2013122","journal-title":"IJDAR"},{"key":"10530_CR136","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo C, Jin L, Sun Z (2019) Moran: a multi-object rectified attention network for scene text recognition. Pattern Recogn 90:109\u2013118","journal-title":"Pattern Recogn"},{"issue":"2","key":"10530_CR137","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":"10530_CR138","doi-asserted-by":"crossref","unstructured":"Lyu P, Liao M, Yao C, Wu W, Bai X (2018a) Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of the European conference on computer vision (ECCV), pp 67\u201383","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"10530_CR139","doi-asserted-by":"crossref","unstructured":"Lyu P, Yao C, Wu W, Yan S, Bai X (2018b) Multi-oriented scene text detection via corner localization and region segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7553\u20137563","DOI":"10.1109\/CVPR.2018.00788"},{"issue":"11","key":"10530_CR140","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 Multimed 20(11):3111\u20133122","journal-title":"IEEE Trans Multimed"},{"key":"10530_CR141","volume":"111","author":"C Ma","year":"2021","unstructured":"Ma C, Sun L, Zhong Z, Huo Q (2021a) Relatext: exploiting visual relationships for arbitrary-shaped scene text detection with graph convolutional networks. Pattern Recogn 111:107684","journal-title":"Pattern Recogn"},{"key":"10530_CR142","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.neucom.2020.09.015","volume":"421","author":"M Ma","year":"2021","unstructured":"Ma M, Wang Q-F, Huang S, Huang S, Goulermas Y, Huang K (2021b) Residual attention-based multi-scale script identification in scene text images. Neurocomputing 421:222\u2013233","journal-title":"Neurocomputing"},{"key":"10530_CR143","doi-asserted-by":"crossref","unstructured":"Mafla A, Dey S, Biten AF, Gomez L, Karatzas D (2021) Multi-modal reasoning graph for scene-text based fine-grained image classification and retrieval. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 4023\u20134033","DOI":"10.1109\/WACV48630.2021.00407"},{"issue":"6","key":"10530_CR144","doi-asserted-by":"crossref","first-page":"4317","DOI":"10.1007\/s10462-021-10000-8","volume":"54","author":"S Mahajan","year":"2021","unstructured":"Mahajan S, Rani R (2021) Text detection and localization in scene images: a broad review. Artif Intell Rev 54(6):4317\u20134377","journal-title":"Artif Intell Rev"},{"key":"10530_CR145","doi-asserted-by":"crossref","unstructured":"Mathew M, Jain M, Jawahar C (2017) Benchmarking scene text recognition in devanagari, telugu and malayalam. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 7. IEEE, pp 42\u201346","DOI":"10.1109\/ICDAR.2017.364"},{"key":"10530_CR146","unstructured":"Mei J, Dai L, Shi B, Bai X (2016) Scene text script identification with convolutional recurrent neural networks. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp 4053\u20134058"},{"key":"10530_CR147","doi-asserted-by":"crossref","unstructured":"Mishra A, Alahari K, Jawahar C (2012a) Scene text recognition using higher order language priors. In: BMVC-British Machine Vision Conference. BMVA","DOI":"10.5244\/C.26.127"},{"key":"10530_CR148","doi-asserted-by":"crossref","unstructured":"Mishra A, Alahari K, Jawahar C (2012b) Top-down and bottom-up cues for scene text recognition. In: 2012 IEEE conference on computer vision and pattern recognition, pp 2687\u20132694","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"10530_CR150","doi-asserted-by":"crossref","unstructured":"Munjal RS, Goyal M, Moharir R, Moharana S (2021) Telcos: on device text localization with clustering of script. arXiv:2104.08045","DOI":"10.1109\/IJCNN52387.2021.9533292"},{"issue":"4","key":"10530_CR151","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.3390\/s21041232","volume":"21","author":"Y Nagaoka","year":"2021","unstructured":"Nagaoka Y, Miyazaki T, Sugaya Y, Omachi S (2021) Text detection using multi-stage region proposal network sensitive to text scale. Sensors 21(4):1232","journal-title":"Sensors"},{"key":"10530_CR152","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114549","volume":"170","author":"F Naiemi","year":"2021","unstructured":"Naiemi F, Ghods V, Khalesi H (2021) A novel pipeline framework for multi oriented scene text image detection and recognition. Expert Syst Appl 170:114549","journal-title":"Expert Syst Appl"},{"key":"10530_CR154","doi-asserted-by":"crossref","unstructured":"Nayef N, Yin F, Bizid I, Choi H, Feng Y, Karatzas D, Luo Z, Pal U, Rigaud C, Chazalon J, et al (2017) Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 1454\u20131459","DOI":"10.1109\/ICDAR.2017.237"},{"key":"10530_CR153","doi-asserted-by":"crossref","unstructured":"Nayef N, Patel Y, Busta M, Chowdhury PN, Karatzas D, Khlif W, Matas J, Pal U, Burie J-C, Liu C-l, et al (2019) Icdar2019 robust reading challenge on multi-lingual scene text detection and recognition-rrc-mlt-2019. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, pp 1582\u20131587","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"10530_CR155","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2010) A method for text localization and recognition in real-world images. In: Asian conference on computer vision. Springer, New York, pp 770\u2013783","DOI":"10.1007\/978-3-642-19318-7_60"},{"key":"10530_CR156","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":"10530_CR157","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"},{"issue":"1","key":"10530_CR158","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62\u201366","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"10530_CR159","doi-asserted-by":"crossref","unstructured":"Pan Y-F, Hou X, Liu C-L (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":"10530_CR160","doi-asserted-by":"crossref","unstructured":"Pan Y-F, Liu C-L, 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":"10530_CR161","first-page":"800","volume":"20","author":"Y-F Pan","year":"2010","unstructured":"Pan Y-F, Hou X, Liu C-L (2010b) 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":"2","key":"10530_CR162","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1007\/s00500-020-05245-4","volume":"25","author":"D Pandey","year":"2021","unstructured":"Pandey D, Pandey BK, Wairya S (2021) Hybrid deep neural network with adaptive galactic swarm optimization for text extraction from scene images. Soft Comput 25(2):1563\u20131580","journal-title":"Soft Comput"},{"key":"10530_CR163","doi-asserted-by":"crossref","unstructured":"Pastor-Pellicer J, Espa\u00f1a-Boquera S, Zamora-Mart\u00ednez F, Afzal MZ, Castro-Bleda MJ (2015) Insights on the use of convolutional neural networks for document image binarization. In: International work-conference on artificial neural networks. Springer, New York, pp 115\u2013126","DOI":"10.1007\/978-3-319-19222-2_10"},{"issue":"13","key":"10530_CR164","doi-asserted-by":"crossref","first-page":"18017","DOI":"10.1007\/s11042-019-7178-3","volume":"78","author":"S Paul","year":"2019","unstructured":"Paul S, Saha S, Basu S, Saha PK, Nasipuri M (2019) Text localization in camera captured images using fuzzy distance transform based adaptive stroke filter. Multimed Tools Appl 78(13):18017\u201318036","journal-title":"Multimed Tools Appl"},{"key":"10530_CR165","doi-asserted-by":"crossref","unstructured":"Pei Z, Cao Z, Long M, Wang J (2018) Multi-adversarial domain adaptation. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11767"},{"key":"10530_CR166","doi-asserted-by":"crossref","unstructured":"Peng X, Cao H, Natarajan P (2017) Using convolutional encoder-decoder for document image binarization. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 708\u2013713","DOI":"10.1109\/ICDAR.2017.121"},{"key":"10530_CR167","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Ding Z, Lu S, Tan CL (2011) Video script identification based on text lines. In: 2011 international conference on document analysis and recognition. IEEE, pp 1240\u20131244","DOI":"10.1109\/ICDAR.2011.250"},{"key":"10530_CR168","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Tan CL (2012) Detecting text in the real world. In: Proceedings of the 20th ACM international conference on multimedia, pp 765\u2013768","DOI":"10.1145\/2393347.2396307"},{"key":"10530_CR169","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":"10530_CR170","doi-asserted-by":"crossref","unstructured":"Pratikakis I, Gatos B, Ntirogiannis K (2013) Icdar 2013 document image binarization contest (dibco 2013). In: 2013 12th international conference on document analysis and recognition. IEEE, pp 1471\u20131476","DOI":"10.1109\/ICDAR.2013.219"},{"key":"10530_CR171","doi-asserted-by":"crossref","first-page":"122685","DOI":"10.1109\/ACCESS.2020.3007351","volume":"8","author":"X Qin","year":"2020","unstructured":"Qin X, Jiang J, Yuan C-A, Qiao S, Fan W (2020) Arbitrary shape natural scene text detection method based on soft attention mechanism and dilated convolution. IEEE Access 8:122685\u2013122694","journal-title":"IEEE Access"},{"issue":"4","key":"10530_CR172","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TCSVT.2018.2817642","volume":"29","author":"K Raghunandan","year":"2018","unstructured":"Raghunandan K, Shivakumara P, Roy S, Kumar GH, Pal U, Lu T (2018) 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"},{"key":"10530_CR173","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2021.100434","volume":"42","author":"E Rainarli","year":"2021","unstructured":"Rainarli E et al (2021) A decade: review of scene text detection methods. Comput. Sci. Rev. 42:100434","journal-title":"Comput. Sci. Rev."},{"issue":"1","key":"10530_CR174","first-page":"1","volume":"6","author":"Z Raisi","year":"2020","unstructured":"Raisi Z, Naiel MA, Fieguth P, Wardell S, Zelek J (2020) 2d positional embedding-based transformer for scene text recognition. J Comput Vis Imaging Syst 6(1):1\u20134","journal-title":"J Comput Vis Imaging Syst"},{"key":"10530_CR175","doi-asserted-by":"crossref","unstructured":"Raisi Z, Naiel MA, Younes G, Wardell S, Zelek JS (2021) Transformer-based text detection in the wild. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3162\u20133171","DOI":"10.1109\/CVPRW53098.2021.00353"},{"issue":"1","key":"10530_CR176","first-page":"53","volume":"3","author":"V Rashmi","year":"2018","unstructured":"Rashmi V, Nayak SN (2018) A hybrid approach to localize text in natural scene images. Int J Eng Appl Sci Technol 3(1):53\u201360","journal-title":"Int J Eng Appl Sci Technol"},{"key":"10530_CR177","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"10530_CR178","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767"},{"key":"10530_CR179","doi-asserted-by":"crossref","unstructured":"Ren X, Ramanan D (2013) Histograms of sparse codes for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3246\u20133253","DOI":"10.1109\/CVPR.2013.417"},{"issue":"18","key":"10530_CR180","doi-asserted-by":"crossref","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan A, Shivakumara P, Chan CS, Tan CL (2014) A robust arbitrary text detection system for natural scene images. Expert Syst Appl 41(18):8027\u20138048","journal-title":"Expert Syst Appl"},{"key":"10530_CR181","doi-asserted-by":"crossref","unstructured":"Risnumawan A, Sulistijono IA, Abawajy J (2016) Text detection in low resolution scene images using convolutional neural network. In: International conference on soft computing and data mining. Springer, New York, pp 366\u2013375","DOI":"10.1007\/978-3-319-51281-5_37"},{"key":"10530_CR182","doi-asserted-by":"crossref","unstructured":"Sajid U, Chow M, Zhang J, Kim T, Wang G (2021) Parallel scale-wise attention network for effective scene text recognition. arXiv:2104.12076","DOI":"10.1109\/IJCNN52387.2021.9534223"},{"key":"10530_CR183","doi-asserted-by":"crossref","first-page":"100895","DOI":"10.1109\/ACCESS.2022.3207469","volume":"10","author":"P Selvam","year":"2022","unstructured":"Selvam P, Koilraj JAS, Romero CAT, Alharbi M, Mehbodniya A, Webber JL, Sengan S (2022) A transformer-based framework for scene text recognition. IEEE Access 10:100895\u2013100910","journal-title":"IEEE Access"},{"key":"10530_CR184","doi-asserted-by":"crossref","unstructured":"Sengupta P, Mollah AF (2021) Scene character recognition with morphological filtering and hog features. In: Soft computing techniques and applications. Springer, New York, pp 1\u20139","DOI":"10.1007\/978-981-15-7394-1_1"},{"key":"10530_CR185","unstructured":"Sermanet P, Chintala S, LeCun Y (2012) Convolutional neural networks applied to house numbers digit classification. In: Proceedings of the 21st international conference on pattern recognition (ICPR2012). IEEE, pp 3288\u20133291"},{"key":"10530_CR186","doi-asserted-by":"crossref","unstructured":"Shahab A, Shafait F, Dengel A (2011) Icdar 2011 robust reading competition challenge 2: Reading text in scene images. In: 2011 international conference on document analysis and recognition, pp 1491\u20131496","DOI":"10.1109\/ICDAR.2011.296"},{"key":"10530_CR187","doi-asserted-by":"crossref","unstructured":"Sharma N, Mandal R, Sharma R, Pal U, Blumenstein M (2015) Icdar2015 competition on video script identification (cvsi 2015). In: 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 1196\u20131200","DOI":"10.1109\/ICDAR.2015.7333950"},{"key":"10530_CR188","doi-asserted-by":"crossref","unstructured":"Sheng F, Chen Z, Xu B (2019) Nrtr: a no-recurrence sequence-to-sequence model for scene text recognition. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, pp 781\u2013786","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"10530_CR200","doi-asserted-by":"crossref","unstructured":"Shi C, Xiao B, Wang C, Zhang Y (2012) Graph-based background suppression for scene text detection. In: 2012 10th IAPR international workshop on document analysis systems. IEEE, pp 210\u2013214","DOI":"10.1109\/DAS.2012.40"},{"key":"10530_CR198","doi-asserted-by":"crossref","unstructured":"Shi C, Wang C, Xiao B, Zhang Y, Gao S, Zhang Z (2013) Scene text recognition using part-based tree-structured character detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2961\u20132968","DOI":"10.1109\/CVPR.2013.381"},{"key":"10530_CR202","doi-asserted-by":"crossref","unstructured":"Shi B, Yao C, Zhang C, Guo X, Huang F, Bai X (2015) Automatic script identification in the wild. In: 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 531\u2013535","DOI":"10.1109\/ICDAR.2015.7333818"},{"key":"10530_CR189","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1016\/j.patcog.2015.11.005","volume":"52","author":"B Shi","year":"2016","unstructured":"Shi B, Bai X, Yao C (2016a) Script identification in the wild via discriminative convolutional neural network. Pattern Recogn 52:448\u2013458","journal-title":"Pattern Recogn"},{"issue":"11","key":"10530_CR190","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi B, Bai X, Yao C (2016b) 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":"10530_CR197","doi-asserted-by":"crossref","unstructured":"Shi B, Wang X, Lyu P, Yao C, Bai X (2016c) 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"},{"key":"10530_CR192","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Belongie S (2017a) Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2550\u20132558","DOI":"10.1109\/CVPR.2017.371"},{"key":"10530_CR201","doi-asserted-by":"crossref","unstructured":"Shi B, Yao C, Liao M, Yang M, Xu P, Cui L, Belongie S, Lu S, Bai X (2017b) Icdar2017 competition on reading Chinese text in the wild (rctw-17). In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 1429\u20131434","DOI":"10.1109\/ICDAR.2017.233"},{"issue":"9","key":"10530_CR191","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi B, Yang M, Wang X, Lyu P, Yao C, Bai X (2018) Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans Pattern Anal Mach Intell 41(9):2035\u20132048","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10530_CR193","doi-asserted-by":"crossref","unstructured":"Shinde A, Patil M (2021) Street view text detection methods. In: 2021 international conference on artificial intelligence and smart systems (ICAIS). IEEE, pp 961\u2013965","DOI":"10.1109\/ICAIS50930.2021.9395776"},{"issue":"2","key":"10530_CR194","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TPAMI.2010.166","volume":"33","author":"P Shivakumara","year":"2010","unstructured":"Shivakumara P, Phan TQ, Tan CL (2010) 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"},{"issue":"8","key":"10530_CR195","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1109\/TCSVT.2012.2198129","volume":"22","author":"P Shivakumara","year":"2012","unstructured":"Shivakumara P, Sreedhar RP, Phan TQ, Lu S, Tan CL (2012) Multioriented video scene text detection through Bayesian classification and boundary growing. IEEE Trans Circuits Syst Video Technol 22(8):1227\u20131235","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10530_CR196","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.cviu.2014.09.003","volume":"130","author":"P Shivakumara","year":"2015","unstructured":"Shivakumara P, Yuan Z, Zhao D, Lu T, Tan CL (2015) New gradient-spatial-structural features for video script identification. Comput Vis Image Underst 130:35\u201353","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"10530_CR203","first-page":"152","volume":"13","author":"GD Simanjuntak","year":"2021","unstructured":"Simanjuntak GD, Nugroho H (2021) Scene text detection with quadtree-based candidate text regions and convolutional neural network. Int J Electr Eng Inf 13(1):152\u2013162","journal-title":"Int J Electr Eng Inf"},{"key":"10530_CR204","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"10530_CR205","doi-asserted-by":"crossref","unstructured":"Singh AK, Mishra A, Dabral P, Jawahar C (2016) A simple and effective solution for script identification in the wild. In: 2016 12th IAPR workshop on document analysis systems (DAS). IEEE, pp 428\u2013433","DOI":"10.1109\/DAS.2016.57"},{"issue":"4","key":"10530_CR206","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1007\/s10489-018-1338-4","volume":"49","author":"R Soni","year":"2019","unstructured":"Soni R, Kumar B, Chand S (2019) Text detection and localization in natural scene images based on text awareness score. Appl Intell 49(4):1376\u20131405","journal-title":"Appl Intell"},{"issue":"6","key":"10530_CR207","doi-asserted-by":"crossref","first-page":"9671","DOI":"10.1007\/s11042-020-10113-2","volume":"80","author":"M Sravani","year":"2021","unstructured":"Sravani M, Maheswararao A, Murthy MK (2021) Robust detection of video text using an efficient hybrid method via key frame extraction and text localization. Multimed Tools Appl 80(6):9671\u20139686","journal-title":"Multimed Tools Appl"},{"key":"10530_CR208","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.jvcir.2019.04.007","volume":"62","author":"B Sriman","year":"2019","unstructured":"Sriman B, Schomaker L (2019) Multi-script text versus non-text classification of regions in scene images. J Vis Commun Image Represent 62:23\u201342","journal-title":"J Vis Commun Image Represent"},{"key":"10530_CR210","doi-asserted-by":"crossref","unstructured":"Su B, Lu S (2014) Accurate scene text recognition based on recurrent neural network. In: Asian conference on computer vision. Springer, New York, pp 35\u201348","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"10530_CR209","doi-asserted-by":"crossref","unstructured":"Su Y-M, Peng H-W, Huang K-W, Yang C-S (2019) Image processing technology for text recognition. In: 2019 international conference on technologies and applications of artificial intelligence (TAAI). IEEE, pp 1\u20135","DOI":"10.1109\/TAAI48200.2019.8959877"},{"issue":"9","key":"10530_CR211","doi-asserted-by":"crossref","first-page":"2906","DOI":"10.1016\/j.patcog.2015.04.002","volume":"48","author":"L Sun","year":"2015","unstructured":"Sun L, Huo Q, Jia W, Chen K (2015) A robust approach for text detection from natural scene images. Pattern Recogn 48(9):2906\u20132920","journal-title":"Pattern Recogn"},{"key":"10530_CR212","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10530_CR213","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.06.020","volume":"96","author":"J Tang","year":"2019","unstructured":"Tang J, Yang Z, Wang Y, Zheng Q, Xu Y, Bai X (2019) Seglink++: detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recogn 96:106954","journal-title":"Pattern Recogn"},{"issue":"22","key":"10530_CR214","doi-asserted-by":"crossref","first-page":"2780","DOI":"10.3390\/electronics10222780","volume":"10","author":"Y Tao","year":"2021","unstructured":"Tao Y, Jia Z, Ma R, Xu S (2021) Trig: transformer-based text recognizer with initial embedding guidance. Electronics 10(22):2780","journal-title":"Electronics"},{"key":"10530_CR215","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/cvf international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10530_CR216","doi-asserted-by":"crossref","unstructured":"Tounsi M, Moalla I, Lebourgeois F, Alimi AM (2017) Cnn based transfer learning for scene script identification. In: International conference on neural information processing. Springer, New York, pp 702\u2013711","DOI":"10.1007\/978-3-319-70136-3_74"},{"key":"10530_CR217","doi-asserted-by":"crossref","unstructured":"Turki H, Halima MB, Alimi AM (2016) Text detection in natural scene images using two masks filtering. In: 2016 IEEE\/ACS 13th international conference of computer systems and applications (AICCSA). IEEE, pp 1\u20136","DOI":"10.1109\/AICCSA.2016.7945644"},{"key":"10530_CR218","doi-asserted-by":"crossref","unstructured":"Turki H, Halima MB, Alimi AM (2017) A hybrid method of natural scene text detection using msers masks in hsv space color. In: Ninth international conference on machine vision (ICMV 2016), vol 10341. International Society for Optics and Photonics, p 1034111","DOI":"10.1117\/12.2268993"},{"key":"10530_CR219","doi-asserted-by":"crossref","unstructured":"Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7167\u20137176","DOI":"10.1109\/CVPR.2017.316"},{"key":"10530_CR220","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30:1\u201310","journal-title":"Adv Neural Inf Process Syst"},{"key":"10530_CR221","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. arXiv:1601.07140"},{"key":"10530_CR222","doi-asserted-by":"crossref","unstructured":"Verma M, Sood N, Roy PP, Raman B (2017) Script identification in natural scene images: a dataset and texture-feature based performance evaluation. In: Proceedings of international conference on computer vision and image processing. Springer, New York, pp 309\u2013319","DOI":"10.1007\/978-981-10-2107-7_28"},{"key":"10530_CR227","doi-asserted-by":"crossref","unstructured":"Wang K, Belongie S (2010) Word spotting in the wild. In: European conference on computer vision. Springer, New York, pp 591\u2013604","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"10530_CR223","first-page":"1","volume":"30","author":"J Wang","year":"2017","unstructured":"Wang J, Hu X (2017) Gated recurrent convolution neural network for ocr. Adv Neural Inf Process Syst 30:1\u201310","journal-title":"Adv Neural Inf Process Syst"},{"key":"10530_CR226","doi-asserted-by":"crossref","unstructured":"Wang K, Babenko B, Belongie S (2011) End-to-end scene text recognition. In: 2011 international conference on computer vision. IEEE, pp 1457\u20131464","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"10530_CR231","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":"10530_CR230","unstructured":"Wang X, Wang B, Bai X, Liu W, Tu Z (2013) Max-margin multiple-instance dictionary learning. In: International conference on machine learning, pp 846\u2013854"},{"key":"10530_CR228","doi-asserted-by":"crossref","unstructured":"Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV), pp 1451\u20131460. IEEE","DOI":"10.1109\/WACV.2018.00163"},{"key":"10530_CR232","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Hou W, Lu T, Yu G, Shao S (2019) Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9336\u20139345","DOI":"10.1109\/CVPR.2019.00956"},{"key":"10530_CR224","volume":"102","author":"S Wang","year":"2020","unstructured":"Wang S, Liu Y, He Z, Wang Y, Tang Z (2020a) A quadrilateral scene text detector with two-stage network architecture. Pattern Recogn 102:107230","journal-title":"Pattern Recogn"},{"key":"10530_CR233","doi-asserted-by":"crossref","unstructured":"Wang T, Zhu Y, Jin L, Luo C, Chen X, Wu Y, Wang Q, Cai M (2020b) Decoupled attention network for text recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 12216\u201312224","DOI":"10.1609\/aaai.v34i07.6903"},{"issue":"3","key":"10530_CR225","doi-asserted-by":"crossref","first-page":"888","DOI":"10.3390\/s21030888","volume":"21","author":"X Wang","year":"2021","unstructured":"Wang X, Zheng S, Zhang C, Li R, Gui L (2021a) R-yolo: a real-time text detector for natural scenes with arbitrary rotation. Sensors 21(3):888","journal-title":"Sensors"},{"key":"10530_CR229","doi-asserted-by":"crossref","unstructured":"Wang P, Li H, Shen C (2021b) Towards end-to-end text spotting in natural scenes. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2021.3095916"},{"key":"10530_CR234","doi-asserted-by":"crossref","unstructured":"Wojna Z, Gorban AN, Lee D-S, Murphy K, Yu Q, Li Y, Ibarz J (2017) Attention-based extraction of structured information from street view imagery. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 844\u2013850","DOI":"10.1109\/ICDAR.2017.143"},{"key":"10530_CR236","doi-asserted-by":"crossref","unstructured":"Wolf C, Doermann D (2002) Binarization of low quality text using a markov random field model. In: Object recognition supported by user interaction for service robots, vol 3. IEEE, pp 160\u2013163","DOI":"10.1109\/ICPR.2002.1047819"},{"issue":"4","key":"10530_CR235","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/s10032-006-0014-0","volume":"8","author":"C Wolf","year":"2006","unstructured":"Wolf C, Jolion J-M (2006) Object count\/area graphs for the evaluation of object detection and segmentation algorithms. IJDAR 8(4):280\u2013296","journal-title":"IJDAR"},{"key":"10530_CR237","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1016\/j.neucom.2016.07.016","volume":"214","author":"H Wu","year":"2016","unstructured":"Wu H, Zou B, Zhao Y-Q, Chen Z, Zhu C, Guo J (2016) Natural scene text detection by multi-scale adaptive color clustering and non-text filtering. Neurocomputing 214:1011\u20131025","journal-title":"Neurocomputing"},{"key":"10530_CR238","unstructured":"Wu F, Souza A, Zhang T, Fifty C, Yu T, Weinberger K (2019a) Simplifying graph convolutional networks. In: International conference on machine learning. PMLR, pp 6861\u20136871"},{"key":"10530_CR239","unstructured":"Wu H, Zhang J, Huang K, Liang K, Yu Y (2019b) Fastfcn: rethinking dilated convolution in the backbone for semantic segmentation. arXiv:1903.11816"},{"key":"10530_CR240","doi-asserted-by":"crossref","unstructured":"Xie S, Tu Z (2015) Holistically-nested edge detection. In: Proceedings of the IEEE international conference on computer vision, pp 1395\u20131403","DOI":"10.1109\/ICCV.2015.164"},{"issue":"11","key":"10530_CR241","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 (2019a) 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":"10530_CR242","doi-asserted-by":"crossref","unstructured":"Xu H, Su X, Liu T, Guo P, Gao G, Bao F (2019b) A natural scene text extraction approach based on generative adversarial learning. In: International conference on neural information processing. Springer, New York, pp 65\u201373","DOI":"10.1007\/978-3-030-36708-4_6"},{"key":"10530_CR246","doi-asserted-by":"crossref","unstructured":"Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 1794\u20131801","DOI":"10.1109\/CVPR.2009.5206757"},{"key":"10530_CR245","doi-asserted-by":"crossref","unstructured":"Yang X, He D, Zhou Z, Kifer D, Giles CL (2017) Learning to read irregular text with attention mechanisms. In: IJCAI, vol 1, p 3","DOI":"10.24963\/ijcai.2017\/458"},{"key":"10530_CR243","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/j.patcog.2018.04.027","volume":"81","author":"B Yang","year":"2018","unstructured":"Yang B, Ma AJ, Yuen PC (2018) Learning domain-shared group-sparse representation for unsupervised domain adaptation. Pattern Recogn 81:615\u2013632","journal-title":"Pattern Recogn"},{"key":"10530_CR244","doi-asserted-by":"crossref","unstructured":"Yang M, Guan Y, Liao M, He X, Bian K, Bai S, Yao C, Bai X (2019) Symmetry-constrained rectification network for scene text recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9147\u20139156","DOI":"10.1109\/ICCV.2019.00924"},{"key":"10530_CR248","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":"10530_CR247","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 (2014a) A unified framework for multioriented text detection and recognition. IEEE Trans Image Process 23(11):4737\u20134749","journal-title":"IEEE Trans Image Process"},{"key":"10530_CR250","doi-asserted-by":"crossref","unstructured":"Yao C, Bai X, Shi B, Liu W (2014b) Strokelets: a learned multi-scale representation for scene text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4042\u20134049","DOI":"10.1109\/CVPR.2014.515"},{"key":"10530_CR251","doi-asserted-by":"crossref","unstructured":"Yao C, Bai X, Shi B, Liu W (2014c) Strokelets: a learned multi-scale representation for scene text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4042\u20134049","DOI":"10.1109\/CVPR.2014.515"},{"key":"10530_CR252","unstructured":"Yao C, Wu J, Zhou X, Zhang C, Zhou S, Cao Z, Yin Q (2015) Incidental scene text understanding: Recent progresses on icdar 2015 robust reading competition challenge 4. arXiv:1511.09207"},{"key":"10530_CR249","unstructured":"Yao C, Bai X, Sang N, Zhou X, Zhou S, Cao Z (2016) Scene text detection via holistic, multi-channel prediction. arXiv:1606.09002"},{"issue":"9","key":"10530_CR253","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":"2","key":"10530_CR254","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"},{"key":"10530_CR255","unstructured":"Yildirim G, Achanta R, S\u00fcsstrunk S (2013) Text recognition in natural images using multiclass hough forests. In: Proceedings of the 8th international conference on computer vision theory and applications, vol 1, pp 737\u2013741"},{"key":"10530_CR258","unstructured":"Yin X, Yin X-C, Hao H-W, Iqbal K (2012) Effective text localization in natural scene images with mser, geometry-based grouping and adaboost. In: Proceedings of the 21st international conference on pattern recognition (ICPR2012). IEEE, pp 725\u2013728"},{"issue":"5","key":"10530_CR256","first-page":"970","volume":"36","author":"X-C Yin","year":"2013","unstructured":"Yin X-C, Yin X, Huang K, Hao H-W (2013) 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":"10530_CR257","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"X-C Yin","year":"2015","unstructured":"Yin X-C, Pei W-Y, Zhang J, Hao H-W (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"},{"key":"10530_CR259","doi-asserted-by":"crossref","unstructured":"Yu F, Koltun V, Funkhouser T (2017) Dilated residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 472\u2013480","DOI":"10.1109\/CVPR.2017.75"},{"key":"10530_CR261","doi-asserted-by":"crossref","unstructured":"Yu D, Li X, Zhang C, Liu T, Han J, Liu J, Ding E (2020) Towards accurate scene text recognition with semantic reasoning networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12113\u201312122","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"10530_CR260","unstructured":"Yuliang L, Lianwen J, Shuaitao Z, Sheng Z (2017) Detecting curve text in the wild: new dataset and new solution. arXiv:1712.02170"},{"key":"10530_CR262","doi-asserted-by":"crossref","unstructured":"Zdenek J, Nakayama H (2017) Bag of local convolutional triplets for script identification in scene text. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR), vol 1. IEEE, pp 369\u2013375","DOI":"10.1109\/ICDAR.2017.68"},{"key":"10530_CR263","unstructured":"Zeiler MD (2012) Adadelta: an adaptive learning rate method. arXiv:1212.5701"},{"key":"10530_CR269","doi-asserted-by":"crossref","unstructured":"Zhan F, Lu S (2019) Esir: end-to-end scene text recognition via iterative image rectification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2059\u20132068","DOI":"10.1109\/CVPR.2019.00216"},{"key":"10530_CR268","doi-asserted-by":"crossref","unstructured":"Zhang C, Yao C, Shi B, Bai X (2015) Automatic discrimination of text and non-text natural images. In: 2015 13th International conference on document analysis and recognition (icdar). IEEE, pp 886\u2013890","DOI":"10.1109\/ICDAR.2015.7333889"},{"key":"10530_CR265","doi-asserted-by":"crossref","unstructured":"Zhang S, Liu Y, Jin L, Luo C (2018) Feature enhancement network: a refined scene text detector. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11887"},{"key":"10530_CR267","doi-asserted-by":"crossref","unstructured":"Zhang Y, Nie S, Liu W, Xu X, Zhang D, Shen HT (2019) Sequence-to-sequence domain adaptation network for robust text image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2740\u20132749","DOI":"10.1109\/CVPR.2019.00285"},{"key":"10530_CR264","doi-asserted-by":"crossref","unstructured":"Zhang S-X, Zhu X, Yang C, Wang H, Yin X-C (2021a) Adaptive boundary proposal network for arbitrary shape text detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1305\u20131314","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"10530_CR266","doi-asserted-by":"crossref","unstructured":"Zhang M, Ma M, Wang P (2021b) Scene text recognition with cascade attention network. In: Proceedings of the 2021 international conference on multimedia retrieval, pp 385\u2013393","DOI":"10.1145\/3460426.3463639"},{"key":"10530_CR271","doi-asserted-by":"crossref","unstructured":"Zhao D, Shivakumara P, Lu S, Tan CL (2012) New spatial-gradient-features for video script identification. In: 2012 10th IAPR international workshop on document analysis systems. IEEE, pp 38\u201342","DOI":"10.1109\/DAS.2012.57"},{"key":"10530_CR270","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"10530_CR272","doi-asserted-by":"crossref","unstructured":"Zharikov I, Nikitin P, Vasiliev I, Dokholyan V (2020) Ddi-100: Dataset for text detection and recognition. In: Proceedings of the 2020 4th international symposium on computer science and intelligent control, pp 1\u20135","DOI":"10.1145\/3440084.3441192"},{"key":"10530_CR273","doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017a) East: an efficient and accurate scene text detector. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5551\u20135560","DOI":"10.1109\/CVPR.2017.283"},{"key":"10530_CR275","doi-asserted-by":"crossref","unstructured":"Zhuo J, Wang S, Zhang W, Huang Q (2017b) Deep unsupervised convolutional domain adaptation. In: Proceedings of the 25th ACM international conference on multimedia, pp 261\u2013269","DOI":"10.1145\/3123266.3123292"},{"key":"10530_CR274","volume":"110","author":"Y Zhu","year":"2021","unstructured":"Zhu Y, Du J (2021) Textmountain: accurate scene text detection via instance segmentation. Pattern Recogn 110:107336","journal-title":"Pattern Recogn"},{"key":"10530_CR276","doi-asserted-by":"publisher","unstructured":"Zhu X, Zhang Z (2021) Transformer-based end-to-end scene text recognition. In: 2021 IEEE 16th conference on industrial electronics and applications (ICIEA), pp 1691\u20131695. https:\/\/doi.org\/10.1109\/ICIEA51954.2021.9516154","DOI":"10.1109\/ICIEA51954.2021.9516154"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-023-10530-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-023-10530-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-023-10530-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T10:35:06Z","timestamp":1696502106000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-023-10530-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":268,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10530"],"URL":"https:\/\/doi.org\/10.1007\/s10462-023-10530-3","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,18]]},"assertion":[{"value":"18 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}