{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T06:29:35Z","timestamp":1766557775780,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"30","license":[{"start":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T00:00:00Z","timestamp":1683072000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T00:00:00Z","timestamp":1683072000000},"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"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11042-023-15449-z","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T09:02:32Z","timestamp":1683104552000},"page":"46871-46903","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep learning based text detection using resnet for feature extraction"],"prefix":"10.1007","volume":"82","author":[{"given":"Li-Kun","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiao-Ting","family":"Tseng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7716-7306","authenticated-orcid":false,"given":"Chen-Chiung","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Sin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,3]]},"reference":[{"key":"15449_CR1","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1016\/0031-3203(93)90178-Y","volume":"26","author":"OE Agazzi","year":"1993","unstructured":"Agazzi OE, Kuo SS (1993) Hidden markov model based optical character recognition in the presence of deterministic transformations. Pattern Recognit 26:1813\u20131826. https:\/\/doi.org\/10.1016\/0031-3203(93)90178-Y","journal-title":"Pattern Recognit"},{"key":"15449_CR2","doi-asserted-by":"publisher","unstructured":"Bahlmann C, Haasdonk B, Burkhardt H (2002) Online handwriting recognition with support vector machines - a kernel approach. International Workshop on Frontiers in Handwriting Recognition (ICFHR 2020), 49\u201354 https:\/\/doi.org\/10.1109\/IWFHR.2002.1030883","DOI":"10.1109\/IWFHR.2002.1030883"},{"key":"15449_CR3","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw Learn Syst 5:157\u2013166. https:\/\/doi.org\/10.1109\/72.279181","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"15449_CR4","doi-asserted-by":"publisher","unstructured":"Bora MB, Daimary D, Amitab K, Kandar D (2020) Handwritten character recognition from images using CNN-ECOC. Procedia Comput Sci 167:2403\u20132409. https:\/\/doi.org\/10.1016\/j.procs.2020.03.293","DOI":"10.1016\/j.procs.2020.03.293"},{"key":"15449_CR5","doi-asserted-by":"publisher","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. IEEE International Conference on Image Processing (ICIP 2011), 2609\u20132612 https:\/\/doi.org\/10.1109\/ICIP.2011.6116200","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"15449_CR6","doi-asserted-by":"publisher","unstructured":"Chen L (2021) Research and application of chinese calligraphy character recognition slgorithm based on image analysis. IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA 2021) 405\u2013410. https:\/\/doi.org\/10.1109\/AEECA52519.2021.9574199","DOI":"10.1109\/AEECA52519.2021.9574199"},{"key":"15449_CR7","doi-asserted-by":"publisher","unstructured":"Deng D, Liu H, Li X, Cai D (2018) PixelLink: detecting scene text via instance segmentation. Conference on Artificial Intelligence (AAAI 2018), https:\/\/doi.org\/10.1609\/aaai.v32i1.12269","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"15449_CR8","doi-asserted-by":"publisher","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010), 2963\u20132970 https:\/\/doi.org\/10.1109\/CVPR.2010.5540041","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"15449_CR9","doi-asserted-by":"publisher","unstructured":"Graves A, Fern\u00e1ndez S, Gomez F, Schmidhuber J (2006) Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural 'networks. International conference on Machine learning (ICML 2006) 369\u2013376, https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"15449_CR10","doi-asserted-by":"publisher","unstructured":"He K, Sun J (2015) Convolutional neural networks at constrained time cost. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) 5353\u20135360, https:\/\/doi.org\/10.48550\/arXiv.1412.1710","DOI":"10.48550\/arXiv.1412.1710"},{"key":"15449_CR11","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning forimage recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) p. 770\u2013778. https:\/\/doi.org\/10.48550\/arXiv.1512.03385","DOI":"10.48550\/arXiv.1512.03385"},{"key":"15449_CR12","doi-asserted-by":"publisher","unstructured":"Hong C, Loudon G, Wu Y, Zitserman R. (1999) Segmentation and recognition of continuous handwritng Chinese text. World Scientific, 223\u2013232. https:\/\/doi.org\/10.1142\/9789812797643_0014","DOI":"10.1142\/9789812797643_0014"},{"key":"15449_CR13","doi-asserted-by":"publisher","unstructured":"Jawahar CV, Kumar MNSSKP, Kiran SSR (2003) A bilingual OCR for Hindi-Telugu documents and its applications. International Conference on Document Analysis and Recognition (ICDAR 2003). 408\u2013412 https:\/\/doi.org\/10.1109\/ICDAR.2003.1227699","DOI":"10.1109\/ICDAR.2003.1227699"},{"key":"15449_CR14","doi-asserted-by":"publisher","unstructured":"Kim KH, Cheon Y, Hong S, Roh BS, Park M (2016) PVANET: Deep but lightweight neural networks for real-time object detection. https:\/\/doi.org\/10.48550\/arXiv.1608.08021","DOI":"10.48550\/arXiv.1608.08021"},{"key":"15449_CR15","doi-asserted-by":"publisher","unstructured":"Laroca R, Severo E, Zanlorensi LA, Oliveira LS, Gon\u00e7alves GR, Schwartz WR, Menotti D (2018) A robust real-time automatic license plate recognition based on the YOLO detector. International Joint Conference on Neural Networks (IJCNN 2018) 1\u201310, https:\/\/doi.org\/10.48550\/arXiv.1802.09567","DOI":"10.48550\/arXiv.1802.09567"},{"key":"15449_CR16","doi-asserted-by":"publisher","unstructured":"Li C (2021) Research on methods of english text detection and recognition based on neural network detection model. Sci Program 2021:6406856. https:\/\/doi.org\/10.1155\/2021\/6406856","DOI":"10.1155\/2021\/6406856"},{"key":"15449_CR17","doi-asserted-by":"publisher","unstructured":"Lin TY, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. IEEE Conf Comput Vis Pattern Recognit (CVPR 2017), 2117\u20132125, https:\/\/doi.org\/10.48550\/arXiv.1612.03144","DOI":"10.48550\/arXiv.1612.03144"},{"key":"15449_CR18","doi-asserted-by":"publisher","unstructured":"Liu CL, Yin F, Wang DH, Wang QF (2011) CASIA online and offline chinese handwriting databases. Int J Doc Anal Recognit (ICDAR 2011) 37\u201341 https:\/\/doi.org\/10.1109\/ICDAR.2011.17. 37\u20134","DOI":"10.1109\/ICDAR.2011.17"},{"key":"15449_CR19","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1109\/ACCESS.2019.2908933","DOI":"10.1109\/ACCESS.2019.2908933"},{"key":"15449_CR20","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), 3431\u20133440, https:\/\/doi.org\/10.48550\/arXiv.1411.4038","DOI":"10.48550\/arXiv.1411.4038"},{"key":"15449_CR21","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. Computer Vision (ECCV 2016),21\u201337, https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15449_CR22","doi-asserted-by":"publisher","first-page":"5962","DOI":"10.3390\/app11135962","volume":"11","author":"M Lu","year":"2021","unstructured":"Lu M, Mou Y, Chen CL, Tang Q (2021) An efficient text detection model for street signs. Appl Sci 11:5962. https:\/\/doi.org\/10.3390\/app11135962","journal-title":"Appl Sci"},{"key":"15449_CR23","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.imavis.2004.02.006","volume":"22","author":"J Matas","year":"2004","unstructured":"Matas J, Chum O, Urban M, Pajdla T (2004) Robust wide-baseline stereo from maximally stable extremal regions. Image Vis Comput 22:761\u2013767. https:\/\/doi.org\/10.1016\/j.imavis.2004.02.006","journal-title":"Image Vis Comput"},{"key":"15449_CR24","doi-asserted-by":"publisher","first-page":"114549","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. https:\/\/doi.org\/10.1016\/j.eswa.2020.114549","journal-title":"Expert Syst. Appl."},{"key":"15449_CR25","doi-asserted-by":"publisher","first-page":"20255","DOI":"10.1007\/s11042-022-12693-7","volume":"81","author":"F Naiemi","year":"2022","unstructured":"Naiemi F, Ghods V, Khalesi H (2022) Scene text detection and recognition: a survey. Multimed Tools Appl 81:20255\u201320290. https:\/\/doi.org\/10.1007\/s11042-022-12693-7","journal-title":"Multimed Tools Appl"},{"key":"15449_CR26","doi-asserted-by":"publisher","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. Systems, Man and Cybernetics IEEE Trans. Syst Man Cybern Syst 9:62\u201366. https:\/\/doi.org\/10.1109\/TSMC.1979.4310076","journal-title":"Syst Man Cybern Syst"},{"key":"15449_CR27","doi-asserted-by":"publisher","unstructured":"Pang B, Wu J (2020) Chinese calligraphy character image recognition and its applications in Web and Wechat Applet Platform. ACM\/IEEE Joint Conference on Digital Libraries (JCDL 2020) 253\u2013260. https:\/\/doi.org\/10.1145\/3383583.3398516","DOI":"10.1145\/3383583.3398516"},{"key":"15449_CR28","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 779\u2013788 https:\/\/doi.org\/10.48550\/arXiv.1506.02640","DOI":"10.48550\/arXiv.1506.02640"},{"key":"15449_CR29","doi-asserted-by":"publisher","unstructured":"Redmon, J., and Farhadi, A.(2017) YOLO9000: Better, faster, stronger. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR 2017) p.6517\u20136525, https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"15449_CR30","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. ArXiv abs\/1804.02767, https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"15449_CR31","doi-asserted-by":"publisher","unstructured":"Ren S , He K, Girshick R, Sun J (2015) \u2018Faster R-CNN: towards real-time object detection with region proposal networks\u2019. International Conference on Neural Information Processing Systems (NIPS 2015) 91\u201399 https:\/\/doi.org\/10.48550\/arXiv.1506.01497","DOI":"10.48550\/arXiv.1506.01497"},{"key":"15449_CR32","unstructured":"Santos CFG (2018) Optical character recognition using deep learning https:\/\/repositorio.unesp.br\/bitstream\/handle\/11449\/154100\/santos_cfg_me_sjrp.pdf?sequence=9"},{"key":"15449_CR33","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45:2673\u20132681. https:\/\/doi.org\/10.1109\/78.650093","journal-title":"IEEE Trans Signal Process"},{"key":"15449_CR34","doi-asserted-by":"publisher","unstructured":"Shi B, Bai X, Yao C (2015) 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. https:\/\/doi.org\/10.1109\/TPAMI.2016.2646371","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"15449_CR35","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556, 0.48550\/arXiv.1409.1556"},{"key":"15449_CR36","doi-asserted-by":"publisher","unstructured":"Tian Z, Huang W, He T, He P, Qiao Y (2016) Detecting text in natural image with connectionist text proposal network. Computer Vision \u2013 ECCV 2016, p. 56\u201372, https:\/\/doi.org\/10.48550\/arXiv.1609.03605","DOI":"10.48550\/arXiv.1609.03605"},{"key":"15449_CR37","unstructured":"Tong X, Evans DA (1996) A statistical approach to automatic OCR error correction in context. VLC@COLING"},{"key":"15449_CR38","doi-asserted-by":"crossref","unstructured":"Wang C, Qi Y, and Wang X (2015) The chinese characters extraction method based on area voronoi diagram in inscription. International Conference on Virtual Reality and Visualization (ICVRV 2015) 109\u2013116","DOI":"10.1109\/ICVRV.2015.45"},{"key":"15449_CR39","doi-asserted-by":"publisher","unstructured":"Wang H, Zhang Z (2019) Text Detection algorithm based on improved YOLOv3. IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC 2019) 147\u2013150, https:\/\/doi.org\/10.1109\/ICEIEC.2019.8784576","DOI":"10.1109\/ICEIEC.2019.8784576"},{"key":"15449_CR40","unstructured":"Wei X, Ma S, Jin Y (2005) Segmentation of connected Chinese characters based on genetic algorithm. International Conference on Document Analysis and Recognition (ICDAR 2005) 645\u2013649"},{"key":"15449_CR41","doi-asserted-by":"publisher","unstructured":"Zhang R, Wang Q, Lu Y (2017) Combination of ResNet and center loss based metric learning for handwritten chinese character recognition. International Conference on Document Analysis and Recognition (ICDAR 2017) 25\u201329, https:\/\/doi.org\/10.1109\/ICDAR.2017.324","DOI":"10.1109\/ICDAR.2017.324"},{"key":"15449_CR42","doi-asserted-by":"publisher","unstructured":"Zhao S, Chi Z, Shi P, Wnag Q (2001) Handwritten Chinese character segmentation using a two-stage approach. Proceedings of Sixth International Conference on Document Analysis and Recognition 179\u2013183. https:\/\/doi.org\/10.1109\/ICDAR.2001.953779","DOI":"10.1109\/ICDAR.2001.953779"},{"key":"15449_CR43","doi-asserted-by":"publisher","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017) EAST: an efficient and accurate scene text detector. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 2642\u20132651 https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15449-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15449-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15449-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T09:13:01Z","timestamp":1701249181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15449-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,3]]},"references-count":43,"journal-issue":{"issue":"30","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["15449"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15449-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,5,3]]},"assertion":[{"value":"20 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors, whose names are listed on this paper, certify that they have no conflicts of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}