{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T01:56:59Z","timestamp":1792893419923,"version":"4.5.0"},"reference-count":173,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T00:00:00Z","timestamp":1598486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T00:00:00Z","timestamp":1598486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11263-020-01369-0","type":"journal-article","created":{"date-parts":[[2020,8,27]],"date-time":"2020-08-27T04:02:51Z","timestamp":1598500971000},"page":"161-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":412,"title":["Scene Text Detection and Recognition: The Deep Learning Era"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4089-5369","authenticated-orcid":false,"given":"Shangbang","family":"Long","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,8,27]]},"reference":[{"issue":"12","key":"1369_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., & Valveny, E. (2014). Word spotting and recognition with embedded attributes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(12), 2552\u20132566.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1369_CR2","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898\u2013916.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1369_CR3","doi-asserted-by":"crossref","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., et al. (2019a). What is wrong with scene text recognition model comparisons? Dataset and model analysis. In Proceedings of the IEEE international conference on computer vision (pp. 4715\u20134723).","DOI":"10.1109\/ICCV.2019.00481"},{"key":"1369_CR4","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019b). Character region awareness for text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 9365\u20139374).","DOI":"10.1109\/CVPR.2019.00959"},{"key":"1369_CR5","unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. In ICLR 2015."},{"key":"1369_CR6","doi-asserted-by":"crossref","unstructured":"Bai, F., Cheng, Z., Niu, Y., Pu, S., & Zhou, S. (2018). Edit probability for scene text recognition. In CVPR 2018.","DOI":"10.1109\/CVPR.2018.00163"},{"key":"1369_CR7","unstructured":"Bartz, C., Yang, H., & Meinel, C. (2017). See: Towards semi-supervised end-to-end scene text recognition. arXiv preprint arXiv:1712.05404."},{"key":"1369_CR8","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":"1369_CR9","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). ACM.","DOI":"10.1145\/3219819.3219861"},{"key":"1369_CR10","doi-asserted-by":"crossref","unstructured":"Busta, M., Neumann, L., & Matas, J. (2015). Fastext: Efficient unconstrained scene text detector. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 1206\u20131214).","DOI":"10.1109\/ICCV.2015.143"},{"key":"1369_CR11","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 ICCV.","DOI":"10.1109\/ICCV.2017.242"},{"issue":"1","key":"1369_CR12","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TIP.2003.819223","volume":"13","author":"X Chen","year":"2004","unstructured":"Chen, X., Yang, J., Zhang, J., & Waibel, A. (2004). Automatic detection and recognition of signs from natural scenes. IEEE Transactions on Image Processing, 13(1), 87\u201399.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1369_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., & Zhou, S. (2017a). Focusing attention: Towards accurate text recognition in natural images. In 2017 IEEE international conference on computer vision (ICCV) (pp. 5086\u20135094). IEEE.","DOI":"10.1109\/ICCV.2017.543"},{"key":"1369_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Liu, X., Bai, F., Niu, Y., Pu, S., & Zhou, S. (2017b). Arbitrarily-oriented text recognition. In CVPR2018.","DOI":"10.1109\/CVPR.2018.00584"},{"key":"1369_CR15","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., & Chan, C. S. (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, pp. 935\u2013942). IEEE.","DOI":"10.1109\/ICDAR.2017.157"},{"issue":"19","key":"1369_CR16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.5120\/13001-0039","volume":"74","author":"MA Chowdhury","year":"2013","unstructured":"Chowdhury, M. A., & Deb, K. (2013). Extracting and segmenting container name from container images. International Journal of Computer Applications, 74(19), 18\u201322.","journal-title":"International Journal of Computer Applications"},{"key":"1369_CR17","doi-asserted-by":"crossref","unstructured":"Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T., et al. (2011). Text detection and character recognition in scene images with unsupervised feature learning. In 2011 international conference on document analysis and recognition (ICDAR) (pp. 440\u2013445). IEEE.","DOI":"10.1109\/ICDAR.2011.95"},{"key":"1369_CR18","doi-asserted-by":"crossref","unstructured":"Dai, Y., Huang, Z., Gao, Y., & Chen, K. (2017). Fused text segmentation networks for multi-oriented scene text detection. arXiv preprint arXiv:1709.03272.","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"1369_CR19","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B., (2005). Histograms of oriented gradients for human detection. In IEEE computer society conference on computer vision and pattern recognition (CVPR) (Vol. 1, pp. 886\u2013893). IEEE.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1369_CR20","first-page":"2018","volume":"I","author":"D Deng","year":"2018","unstructured":"Deng, D., Liu, H., Li, X., & Cai, D. (2018). Pixellink: Detecting scene text via instance segmentation. Proceedings of AAA, I, 2018.","journal-title":"Proceedings of AAA"},{"issue":"2","key":"1369_CR21","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/34.982903","volume":"24","author":"GN DeSouza","year":"2002","unstructured":"DeSouza, G. N., & Kak, A. C. (2002). Vision for mobile robot navigation: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(2), 237\u2013267.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"1369_CR22","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r, P., Appel, R., Belongie, S., & Perona, P. (2014). Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1532\u20131545.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1369_CR23","unstructured":"Dvorin, Y., & Havosha, U. E. (2009). Method and device for instant translation, June\u00a04. US Patent App. 11\/998,931."},{"key":"1369_CR24","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., & Wexler, Y. (2010). Detecting text in natural scenes with stroke width transform. In 2010 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2963\u20132970). IEEE.","DOI":"10.1109\/CVPR.2010.5540041"},{"issue":"1","key":"1369_CR25","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"1369_CR26","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/B:VISI.0000042934.15159.49","volume":"61","author":"PF Felzenszwalb","year":"2005","unstructured":"Felzenszwalb, P. F., & Huttenlocher, D. P. (2005). Pictorial structures for object recognition. International Journal of Computer Vision, 61(1), 55\u201379.","journal-title":"International Journal of Computer Vision"},{"key":"1369_CR27","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). DSSD: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659."},{"key":"1369_CR28","unstructured":"Gao, Y., Chen, Y., Wang, J., & Lu, H. (2017). Reading scene text with attention convolutional sequence modeling. arXiv preprint arXiv:1709.04303."},{"key":"1369_CR29","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In The IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.169"},{"key":"1369_CR30","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 580\u2013587).","DOI":"10.1109\/CVPR.2014.81"},{"issue":"1","key":"1369_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jagm.1995.0805","volume":"22","author":"AV Goldberg","year":"1997","unstructured":"Goldberg, A. V. (1997). An efficient implementation of a scaling minimum-cost flow algorithm. Journal of Algorithms, 22(1), 1\u201329.","journal-title":"Journal of Algorithms"},{"key":"1369_CR32","doi-asserted-by":"crossref","unstructured":"Gordo, A. (2015). Supervised mid-level features for word image representation. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2956\u20132964).","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"1369_CR33","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., & Schmidhuber, J. (2006). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd international conference on machine learning (pp. 369\u2013376). ACM.","DOI":"10.1145\/1143844.1143891"},{"key":"1369_CR34","unstructured":"Graves, A., Liwicki, M., Bunke, H., Schmidhuber, J., & Fern\u00e1ndez, S. (2008). Unconstrained on-line handwriting recognition with recurrent neural networks. In Advances in neural information processing systems (pp. 577\u2013584)."},{"key":"1369_CR35","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 (CVPR) (pp. 2315\u20132324).","DOI":"10.1109\/CVPR.2016.254"},{"issue":"1","key":"1369_CR36","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1117\/12.184094","volume":"34","author":"YK Ham","year":"1995","unstructured":"Ham, Y. K., Kang, M. S., Chung, H. K., Park, R.-H., & Park, G. T. (1995). Recognition of raised characters for automatic classification of rubber tires. Optical Engineering, 34(1), 102\u2013110.","journal-title":"Optical Engineering"},{"issue":"1","key":"1369_CR37","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han, J., Zhang, D., Cheng, G., Liu, N., & Xu, D. (2018). Advanced deep-learning techniques for salient and category-specific object detection: A survey. IEEE Signal Processing Magazine, 35(1), 84\u2013100.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1369_CR38","doi-asserted-by":"crossref","unstructured":"He, D., Yang, X., Liang, C., Zhou, Z., Ororbia, A.\u00a0G., Kifer, D., & Giles, C.\u00a0L. (2017a). Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild. In 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 474\u2013483). IEEE.","DOI":"10.1109\/CVPR.2017.58"},{"key":"1369_CR39","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017b). Mask R-CNN. In 2017 IEEE international conference on computer vision (ICCV) (pp. 2980\u20132988). IEEE.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1369_CR40","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., & Li, X. (2017c). Single shot text detector with regional attention. In The IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.331"},{"key":"1369_CR41","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.\u00a0C., & Tang, X. (2016). Reading scene text in deep convolutional sequences. In Thirtieth AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"1369_CR42","doi-asserted-by":"crossref","unstructured":"He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., & Sun, C. (2018). An end-to-end textspotter with explicit alignment and attention. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5020\u20135029).","DOI":"10.1109\/CVPR.2018.00527"},{"key":"1369_CR43","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.-Y., Yin, F., & Liu, C.-L. (2017d). Deep direct regression for multi-oriented scene text detection. In The IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.87"},{"issue":"1","key":"1369_CR44","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/TITS.2004.838509","volume":"6","author":"Z He","year":"2005","unstructured":"He, Z., Liu, J., Ma, H., & Li, P. (2005). A new automatic extraction method of container identity codes. IEEE Transactions on Intelligent Transportation Systems, 6(1), 72\u201378.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"8","key":"1369_CR45","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1369_CR46","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C., Luo, Y., Wang, Y., Han, J., & Ding, E. (2017). Wordsup: Exploiting word annotations for character based text detection. In Proceedings of the IEEE international conference on computer vision. 2017.","DOI":"10.1109\/ICCV.2017.529"},{"key":"1369_CR47","doi-asserted-by":"crossref","unstructured":"Huang, W., Lin, Z., Yang, J., & Wang, J. (2013). Text localization in natural images using stroke feature transform and text covariance descriptors. In Proceedings of the IEEE international conference on computer vision (pp. 1241\u20131248).","DOI":"10.1109\/ICCV.2013.157"},{"key":"1369_CR48","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 (pp. 497\u2013511). Springer.","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"1369_CR49","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014a). Deep structured output learning for unconstrained text recognition. In ICLR2015."},{"key":"1369_CR50","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014b). Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227."},{"issue":"1","key":"1369_CR51","doi-asserted-by":"publisher","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. International Journal of Computer Vision, 116(1), 1\u201320.","journal-title":"International Journal of Computer Vision"},{"key":"1369_CR52","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A. et\u00a0al. (2015). Spatial transformer networks. In Advances in neural information processing systems (pp. 2017\u20132025)."},{"key":"1369_CR53","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014c). Deep features for text spotting. In In Proceedings of European conference on computer vision (ECCV) (pp. 512\u2013528). Springer.","DOI":"10.1007\/978-3-319-10593-2_34"},{"issue":"12","key":"1369_CR54","doi-asserted-by":"publisher","first-page":"2055","DOI":"10.1016\/S0031-3203(98)00067-3","volume":"31","author":"AK Jain","year":"1998","unstructured":"Jain, A. K., & Yu, B. (1998). Automatic text location in images and video frames. Pattern Recognition, 31(12), 2055\u20132076.","journal-title":"Pattern Recognition"},{"key":"1369_CR55","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhu, X., Wang, X., Yang, S., Li, W., Wang, H., Fu, P., & Luo, Z. (2017). R2CNN: rotational region CNN for orientation robust scene text detection. arXiv preprint arXiv:1706.09579.","DOI":"10.1109\/ICPR.2018.8545598"},{"issue":"5","key":"1369_CR56","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/j.patcog.2003.10.012","volume":"37","author":"K Jung","year":"2004","unstructured":"Jung, K., Kim, K. I., & Jain, A. K. (2004). Text information extraction in images and video: A survey. Pattern Recognition, 37(5), 977\u2013997.","journal-title":"Pattern Recognition"},{"key":"1369_CR57","doi-asserted-by":"crossref","unstructured":"Kang, L., Li, Y., & Doermann, D. (2014). Orientation robust text line detection in natural images. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4034\u20134041).","DOI":"10.1109\/CVPR.2014.514"},{"key":"1369_CR58","doi-asserted-by":"crossref","unstructured":"Karatzas, D., & Antonacopoulos, A. (2004). Text extraction from web images based on a split-and-merge segmentation method using colour perception. In Proceedings of the 17th international conference on pattern recognition, 2004. ICPR 2004 (Vol. 2, pp. 634\u2013637). IEEE.","DOI":"10.1109\/ICPR.2004.1334328"},{"key":"1369_CR59","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., et\u00a0al. (2015). ICDAR 2015 competition on robust reading. In 2015 13th international conference on document analysis and recognition (ICDAR) (pp. 1156\u20131160). IEEE.","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1369_CR60","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Bigorda, L.\u00a0G. I., Mestre, S.\u00a0R., et al. (2013). ICDAR 2013 robust reading competition. In 2013 12th international conference on document analysis and recognition (ICDAR) (pp. 1484\u20131493). IEEE.","DOI":"10.1109\/ICDAR.2013.221"},{"key":"1369_CR61","unstructured":"Kipf, T.\u00a0N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907."},{"key":"1369_CR62","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G.\u00a0E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097\u20131105)."},{"key":"1369_CR63","doi-asserted-by":"crossref","unstructured":"Lee, C.-Y., & Osindero, S. (2016). Recursive recurrent nets with attention modeling for OCR in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2231\u20132239).","DOI":"10.1109\/CVPR.2016.245"},{"key":"1369_CR64","doi-asserted-by":"crossref","unstructured":"Lee, J.-J, Lee, P.-H., Lee, S.-W., Yuille, A., & Koch, C. (2011). Adaboost for text detection in natural scene. In 2011 international conference on document analysis and recognition (ICDAR) (pp. 429\u2013434). IEEE.","DOI":"10.1109\/ICDAR.2011.93"},{"issue":"11","key":"1369_CR65","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1016\/j.imavis.2013.08.007","volume":"31","author":"S Lee","year":"2013","unstructured":"Lee, S., & Kim, J. H. (2013). Integrating multiple character proposals for robust scene text extraction. Image and Vision Computing, 31(11), 823\u2013840.","journal-title":"Image and Vision Computing"},{"key":"1369_CR66","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., & Shen, C. (2017a). Towards end-to-end text spotting with convolutional recurrent neural networks. In The IEEE international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.560"},{"key":"1369_CR67","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., & Zhang, G. (2019). Show, attend and read: A simple and strong baseline for irregular text recognition. In AAAI.","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"1369_CR68","unstructured":"Li, R., En, M., Li, J., & Zhang, H. (2017b). Weakly supervised text attention network for generating text proposals in scene images. In 2017 14th IAPR international conference on document analysis and recognition (ICDAR) (Vol. 1, pp. 324\u2013330). IEEE."},{"issue":"8","key":"1369_CR69","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao, M., Shi, B., & Bai, X. (2018a). Textboxes++: A single-shot oriented scene text detector. IEEE Transactions on Image Processing, 27(8), 3676\u20133690.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1369_CR70","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., & Liu, W. (2017). Textboxes: A fast text detector with a single deep neural network. In AAAI (pp. 4161\u20134167).","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"1369_CR71","doi-asserted-by":"crossref","unstructured":"Liao, M., Song, B., He, M., Long, S., Yao, C., & Bai, X. (2019a). Synthtext3d: Synthesizing scene text images from 3d virtual worlds. arXiv preprint arXiv:1907.06007.","DOI":"10.1007\/s11432-019-2737-0"},{"key":"1369_CR72","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., & Bai, X. (2019b). Scene text recognition from two-dimensional perspective. In AAAI.","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"1369_CR73","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhu, Z., Shi, B., Xia, G.-S., & Bai, X. (2018b). Rotation-sensitive regression for oriented scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5909\u20135918).","DOI":"10.1109\/CVPR.2018.00619"},{"key":"1369_CR74","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., & Lin, G. (2015). Deep convolutional neural fields for depth estimation from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5162\u20135170).","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"1369_CR75","doi-asserted-by":"crossref","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietik\u00e4inen, M. (2018a). Deep learning for generic object detection: A survey. arXiv preprint arXiv:1809.02165.","DOI":"10.1007\/s11263-019-01247-4"},{"key":"1369_CR76","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A.\u00a0C. (2016a). SSD: Single shot multibox detector. In In Proceedings of European conference on computer vision (ECCV) (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1369_CR77","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., & Wong, K. (2018b). Char-net: A character-aware neural network for distorted scene text recognition. In AAAI conference on artificial intelligence, New Orleans, Louisiana, USA.","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"1369_CR78","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.-Y.\u00a0K., Su, Z., & Han, J. (2016b). Star-net: A spatial attention residue network for scene text recognition. In BMVC (Vol.\u00a02, p.\u00a07).","DOI":"10.5244\/C.30.43"},{"key":"1369_CR79","volume-title":"Old book of tang","author":"X Liu","year":"1975","unstructured":"Liu, X. (1975). Old book of tang. Beijing: Zhonghua Book Company."},{"key":"1369_CR80","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., & Yan, J. (2018c). FOTS: Fast oriented text spotting with a unified network. In CVPR2018.","DOI":"10.1109\/CVPR.2018.00595"},{"key":"1369_CR81","doi-asserted-by":"crossref","unstructured":"Liu, X., & Samarabandu, J. (2005a). An edge-based text region extraction algorithm for indoor mobile robot navigation. In 2005 IEEE international conference mechatronics and automation (Vol. 2, pp. 701\u2013706). IEEE.","DOI":"10.1109\/ICMA.2005.1626635"},{"key":"1369_CR82","doi-asserted-by":"crossref","unstructured":"Liu, X., & Samarabandu, J.\u00a0K. (2005b). A simple and fast text localization algorithm for indoor mobile robot navigation. In Image processing: Algorithms and systems IV (Vol. 5672, pp. 139\u2013151). International Society for Optics and Photonics.","DOI":"10.1117\/12.594572"},{"key":"1369_CR83","doi-asserted-by":"crossref","unstructured":"Liu, Y., & Jin, L. (2017). Deep matching prior network: Toward tighter multi-oriented text detection.","DOI":"10.1109\/CVPR.2017.368"},{"key":"1369_CR84","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., Xie, Z., Luo, C., Zhang, S., & Xie, L. (2019). Tightness-aware evaluation protocol for scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9612\u20139620).","DOI":"10.1109\/CVPR.2019.00984"},{"key":"1369_CR85","unstructured":"Liu, Y., Jin, L., Zhang, S., & Zhang, S. (2017). Detecting curve text in the wild: New dataset and new solution. arXiv preprint arXiv:1712.02170."},{"key":"1369_CR86","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, Y., Ren, F., Yu, H., & Goh, W. (2018d). Squeezedtext: A real-time scene text recognition by binary convolutional encoder\u2013decoder network. In AAAI.","DOI":"10.1609\/aaai.v32i1.12252"},{"key":"1369_CR87","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, G., Yang, S., Feng, J., Lin, W., & Goh, W.\u00a0L. (2018e). Learning Markov clustering networks for scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6936\u20136944).","DOI":"10.1109\/CVPR.2018.00725"},{"key":"1369_CR88","doi-asserted-by":"crossref","unstructured":"Long, S., Guan, Y., Bian, K., & Yao, C. (2020). A new perspective for flexible feature gathering in scene text recognition via character anchor pooling. In ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2458\u20132462. IEEE.","DOI":"10.1109\/ICASSP40776.2020.9054135"},{"key":"1369_CR89","unstructured":"Long, S., Guan, Y., Wang, B., Bian, K., & Yao, C. (2019). Alchemy: Techniques for rectification based irregular scene text recognition. arXiv preprint arXiv:1908.11834."},{"key":"1369_CR90","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 European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"1369_CR91","unstructured":"Long, S., & Yao, C. (2020). Unrealtext: Synthesizing realistic scene text images from the unreal world. arXiv preprint arXiv:2003.10608."},{"key":"1369_CR92","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 European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"1369_CR93","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 2018 IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00788"},{"key":"1369_CR94","doi-asserted-by":"publisher","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., et al. (2018). Arbitrary-oriented scene text detection via rotation proposals. IEEE Transactions on Multimedia, 20, 3111\u20133122.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1369_CR95","doi-asserted-by":"crossref","unstructured":"Mammeri, A., & Boukerche, A. et\u00a0al. (2016). MSER-based text detection and communication algorithm for autonomous vehicles. In 2016 IEEE symposium on computers and communication (ISCC) (pp. 1218\u20131223). IEEE.","DOI":"10.1109\/ISCC.2016.7543902"},{"key":"1369_CR96","doi-asserted-by":"crossref","unstructured":"Mammeri, A., Khiari, E.-H., & Boukerche, A. (2014). Road-sign text recognition architecture for intelligent transportation systems. In 2014 IEEE 80th vehicular technology conference (VTC Fall) (pp. 1\u20135). IEEE.","DOI":"10.1109\/VTCFall.2014.6966161"},{"key":"1369_CR97","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. (2011). An MRF model for binarization of natural scene text. In ICDAR-international conference on document analysis and recognition. IEEE.","DOI":"10.1109\/ICDAR.2011.12"},{"key":"1369_CR98","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. (2012). Scene text recognition using higher order language priors. In BMVC-British machine vision conference. BMVA.","DOI":"10.5244\/C.26.127"},{"key":"1369_CR99","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 (pp. 770\u2013783). Springer.","DOI":"10.1007\/978-3-642-19318-7_60"},{"key":"1369_CR100","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 (CVPR) (pp. 3538\u20133545). IEEE.","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"1369_CR101","doi-asserted-by":"crossref","unstructured":"Neumann, L., & Matas, J. (2013). On combining multiple segmentations in scene text recognition. In 2013 12th international conference on document analysis and recognition (ICDAR) (pp. 523\u2013527). IEEE.","DOI":"10.1109\/ICDAR.2013.110"},{"issue":"11","key":"1369_CR102","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.1016\/j.patcog.2005.01.026","volume":"38","author":"S Nomura","year":"2005","unstructured":"Nomura, S., Yamanaka, K., Katai, O., Kawakami, H., & Shiose, T. (2005). A novel adaptive morphological approach for degraded character image segmentation. Pattern Recognition, 38(11), 1961\u20131975.","journal-title":"Pattern Recognition"},{"key":"1369_CR103","unstructured":"Parkinson, C., Jacobsen, J.\u00a0J., Ferguson, D.\u00a0B., & Pombo, S.\u00a0A. (2016). Instant translation system, Nov.\u00a029. US Patent 9,507,772."},{"key":"1369_CR104","doi-asserted-by":"crossref","unstructured":"Qin, S., Bissacco, A., Raptis, M., Fujii, Y., & Xiao, Y. (2019). Towards unconstrained end-to-end text spotting. In Proceedings of the IEEE international conference on computer vision (pp. 4704\u20134714).","DOI":"10.1109\/ICCV.2019.00480"},{"key":"1369_CR105","doi-asserted-by":"crossref","unstructured":"Qiu, W., Zhong, F., Zhang, Y., Qiao, S., Xiao, Z., Kim, T.\u00a0S., & Wang, Y. (2017). Unrealcv: Virtual worlds for computer vision. In Proceedings of the 25th ACM international conference on multimedia (pp. 1221\u20131224). ACM.","DOI":"10.1145\/3123266.3129396"},{"key":"1369_CR106","doi-asserted-by":"crossref","unstructured":"Phan, T. Q., Shivakumara, P., Tian, S., & Tan, C. L. (2013). Recognizing text with perspective distortion in natural scenes. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 569\u2013576).","DOI":"10.1109\/ICCV.2013.76"},{"key":"1369_CR107","doi-asserted-by":"crossref","unstructured":"Redmon, J., & Farhadi, A. (2017). Yolo9000: Better, faster, stronger. arXiv preprint.","DOI":"10.1109\/CVPR.2017.690"},{"key":"1369_CR108","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 779\u2013788).","DOI":"10.1109\/CVPR.2016.91"},{"key":"1369_CR109","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91\u201399)."},{"issue":"3","key":"1369_CR110","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11263-014-0793-6","volume":"113","author":"JA Rodriguez-Serrano","year":"2015","unstructured":"Rodriguez-Serrano, J. A., Gordo, A., & Perronnin, F. (2015). Label embedding: A frugal baseline for text recognition. International Journal of Computer Vision, 113(3), 193\u2013207.","journal-title":"International Journal of Computer Vision"},{"key":"1369_CR111","doi-asserted-by":"crossref","unstructured":"Rodriguez-Serrano, J. A., Perronnin, F., & Meylan, F. (2013). Label embedding for text recognition. In Proceedings of the British machine vision conference. Citeseer.","DOI":"10.5244\/C.27.5"},{"key":"1369_CR112","volume-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Berlin: Springer."},{"key":"1369_CR113","doi-asserted-by":"crossref","unstructured":"Roy, P.\u00a0P., Pal, U., Llados, J., & Delalandre, M. (2009). Multi-oriented and multi-sized touching character segmentation using dynamic programming. In 10th international conference on document analysis and recognition, 2009. IEEE.","DOI":"10.1109\/ICDAR.2009.124"},{"issue":"3","key":"1369_CR114","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1369_CR115","doi-asserted-by":"crossref","unstructured":"Schroth, G., Hilsenbeck, S., Huitl, R., Schweiger, F., & Steinbach, E. (2011). Exploiting text-related features for content-based image retrieval. In 2011 IEEE international symposium on multimedia (pp. 77\u201384). IEEE.","DOI":"10.1109\/ISM.2011.21"},{"key":"1369_CR116","doi-asserted-by":"crossref","unstructured":"Schulz, R., Talbot, B., Lam, O., Dayoub, F., Corke, P., Upcroft, B., & Wyeth, G. (2015). Robot navigation using human cues: A robot navigation system for symbolic goal-directed exploration. In Proceedings of the 2015 IEEE international conference on robotics and automation (ICRA 2015) (pp. 1100\u20131105). IEEE.","DOI":"10.1109\/ICRA.2015.7139313"},{"key":"1369_CR117","doi-asserted-by":"crossref","unstructured":"Sheshadri, K., & Divvala, S.\u00a0K. (2012). Exemplar driven character recognition in the wild. In BMVC (pp. 1\u201310).","DOI":"10.5244\/C.26.13"},{"key":"1369_CR118","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., & Belongie, S. (2017a). Detecting oriented text in natural images by linking segments. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.371"},{"issue":"11","key":"1369_CR119","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., & Yao, C. (2017b). An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2298\u20132304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1369_CR120","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., & Bai, X. (2016). Robust scene text recognition with automatic rectification. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4168\u20134176).","DOI":"10.1109\/CVPR.2016.452"},{"issue":"11","key":"1369_CR121","first-page":"855","volume":"31","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Bai, X., & Yao, C. (2018). Aster: An attentional scene text recognizer with flexible rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(11), 855\u2013868.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1369_CR122","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 2013 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2961\u20132968). IEEE.","DOI":"10.1109\/CVPR.2013.381"},{"key":"1369_CR123","doi-asserted-by":"crossref","unstructured":"Shivakumara, P., Bhowmick, S., Su, B., Tan, C.\u00a0L., & Pal, U. (2011). A new gradient based character segmentation method for video text recognition. In 2011 international conference on document analysis and recognition (ICDAR). IEEE.","DOI":"10.1109\/ICDAR.2011.34"},{"key":"1369_CR124","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 (pp. 35\u201348). Springer.","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"1369_CR125","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., & Liu, J. (2019). Chinese street view text: Large-scale Chinese text reading with partially supervised learning. In Proceedings of the IEEE international conference on computer vision (pp. 9086\u20139095).","DOI":"10.1109\/ICCV.2019.00918"},{"key":"1369_CR126","unstructured":"Sutskever, I., Vinyals, O., & Le, Q.\u00a0V. (2014). Sequence to sequence learning with neural networks. In Advances in neural information processing systems (pp. 3104\u20133112)."},{"key":"1369_CR127","doi-asserted-by":"crossref","unstructured":"Tian, S., Pan, Y., Huang, C., Lu, S., Yu, K., & Tan, C.\u00a0L. (2015). Text flow: A unified text detection system in natural scene images. In Proceedings of the IEEE international conference on computer vision (pp. 4651\u20134659).","DOI":"10.1109\/ICCV.2015.528"},{"key":"1369_CR128","doi-asserted-by":"crossref","unstructured":"Tian, S., Lu, S., & Li, C. (2017). Wetext: Scene text detection under weak supervision. In Proceedings of ICCV.","DOI":"10.1109\/ICCV.2017.166"},{"key":"1369_CR129","doi-asserted-by":"crossref","unstructured":"Tian, Z. Huang, W., He, T., He, P., & Qiao, Y. (2016). Detecting text in natural image with connectionist text proposal network. In In Proceedings of European conference on computer vision (ECCV) (pp. 56\u201372). Springer.","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"1369_CR130","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shu, M., Lyu, P., Li, R., Zhou, C., Shen, X., & Jia, J. (2019). Learning shape-aware embedding for scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4234\u20134243).","DOI":"10.1109\/CVPR.2019.00436"},{"key":"1369_CR131","doi-asserted-by":"crossref","unstructured":"Tsai, S.\u00a0S., Chen, H., Chen, D., Schroth, G., Grzeszczuk, R., & Girod, B. (2011). Mobile visual search on printed documents using text and low bit-rate features. In 18th IEEE international conference on image processing (ICIP) (pp. 2601\u20132604). IEEE.","DOI":"10.1109\/ICIP.2011.6116198"},{"key":"1369_CR132","unstructured":"Tu, Z., Ma, Y., Liu, W., Bai, X., & Yao, C. (2012). Detecting texts of arbitrary orientations in natural images. In 2012 IEEE conference on computer vision and pattern recognition (pp. 1083\u20131090). IEEE."},{"key":"1369_CR133","doi-asserted-by":"crossref","unstructured":"Uchida, S. (2014). Text localization and recognition in images and video. In Handbook of document image processing and recognition (pp. 843\u2013883). Springer.","DOI":"10.1007\/978-0-85729-859-1_28"},{"key":"1369_CR134","doi-asserted-by":"crossref","unstructured":"Wachenfeld, S., Klein, H.-U., & Jiang, X. (2006). Recognition of screen-rendered text. In 18th international conference on pattern recognition, 2006. ICPR 2006 (Vol. 2, pp. 1086\u20131089). IEEE.","DOI":"10.1109\/ICPR.2006.974"},{"key":"1369_CR135","doi-asserted-by":"crossref","unstructured":"Wakahara, T., & Kita, K. (2011). Binarization of color character strings in scene images using k-means clustering and support vector machines. In 2011 international conference on document analysis and recognition (ICDAR) (pp. 274\u2013278). IEEE.","DOI":"10.1109\/ICDAR.2011.63"},{"key":"1369_CR136","doi-asserted-by":"crossref","unstructured":"Wang, C., Yin, F., & Liu, C.-L. (2017). Scene text detection with novel superpixel based character candidate extraction. In 2017 14th IAPR international conference on document analysis and recognition (ICDAR) (Vol. 1, pp. 929\u2013934). IEEE.","DOI":"10.1109\/ICDAR.2017.156"},{"key":"1369_CR137","doi-asserted-by":"crossref","unstructured":"Wang, F., Zhao, L., Li, X., Wang, X., & Tao, D. (2018). Geometry-aware scene text detection with instance transformation network. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1381\u20131389).","DOI":"10.1109\/CVPR.2018.00150"},{"key":"1369_CR138","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., & Belongie, S. (2011). End-to-end scene text recognition. In 2011 IEEE international conference on computer vision (ICCV), (pp. 1457\u20131464). IEEE.","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"1369_CR139","unstructured":"Wang, T., Wu, D. J., Coates, A., & Ng, A. Y. (2012). End-to-end text recognition with convolutional neural networks. In 2012 21st international conference on pattern recognition (ICPR) (pp. 3304\u20133308). IEEE."},{"key":"1369_CR140","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., & Shao, S. (2019a). Shape robust text detection with progressive scale expansion network. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1369_CR141","doi-asserted-by":"crossref","unstructured":"Wang, X., Jiang, Y., Luo, Z., Liu, C.-L., Choi, H., & Kim, S. (2019b). Arbitrary shape scene text detection with adaptive text region representation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6449\u20136458).","DOI":"10.1109\/CVPR.2019.00661"},{"key":"1369_CR142","doi-asserted-by":"crossref","unstructured":"Weinman, J., Learned-Miller, E., & Hanson, A. (2007). Fast lexicon-based scene text recognition with sparse belief propagation. In ICDAR (pp. 979\u2013983). IEEE.","DOI":"10.1109\/ICDAR.2007.4377061"},{"issue":"4","key":"1369_CR143","doi-asserted-by":"publisher","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. International Journal of Document Analysis and Recognition (IJDAR), 8(4), 280\u2013296.","journal-title":"International Journal of Document Analysis and Recognition (IJDAR)"},{"key":"1369_CR144","doi-asserted-by":"crossref","unstructured":"Wu, L., Zhang, C., Liu, J., Han, J., Liu, J., Ding, E., & Bai, X. (2019). Editing text in the wild. In Proceedings of the 27th ACM international conference on multimedia (pp. 1500\u20131508).","DOI":"10.1145\/3343031.3350929"},{"key":"1369_CR145","doi-asserted-by":"crossref","unstructured":"Wu, Y., & Natarajan, P. (2017). Self-organized text detection with minimal post-processing via border learning. In Proceedings of the IEEE conference on CVPR (pp. 5000\u20135009).","DOI":"10.1109\/ICCV.2017.535"},{"key":"1369_CR146","unstructured":"Xia, Y., Tian, F., Wu, L., Lin, J., Qin, T., Yu, N., & Liu, T.-Y. (2017). Deliberation networks: Sequence generation beyond one-pass decoding. In Advances in neural information processing systems (pp. 1784\u20131794)."},{"key":"1369_CR147","doi-asserted-by":"crossref","unstructured":"Xing, L., Tian, Z., Huang, W., & Scott, M. R. (2019). Convolutional character networks. In Proceedings of the IEEE international conference on computer vision (pp. 9126\u20139136).","DOI":"10.1109\/ICCV.2019.00922"},{"key":"1369_CR148","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., et al. (2015). Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning (pp. 2048\u20132057)."},{"key":"1369_CR149","doi-asserted-by":"crossref","unstructured":"Xue, C., Lu, S., & Zhan, F. (2018). Accurate scene text detection through border semantics awareness and bootstrapping. In In Proceedings of European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"1369_CR150","doi-asserted-by":"crossref","unstructured":"Yang, M., Guan, Y., Liao, M., He, X., Bian, K., Bai, S., et al. (2019). Symmetry-constrained rectification network for scene text recognition. In Proceedings of the IEEE international conference on computer vision (pp. 9147\u20139156).","DOI":"10.1109\/ICCV.2019.00924"},{"key":"1369_CR151","doi-asserted-by":"crossref","unstructured":"Yang, Q., Jin, H., Huang, J., & Lin, W. (2020). Swaptext: Image based texts transfer in scenes. arXiv preprint arXiv:2003.08152.","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"1369_CR152","doi-asserted-by":"crossref","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., & Giles, C. L. (2017). Learning to read irregular text with attention mechanisms. In Proceedings of the twenty-sixth international joint conference on artificial intelligence, IJCAI-17 (pp. 3280\u20133286).","DOI":"10.24963\/ijcai.2017\/458"},{"key":"1369_CR153","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., & Liu, W. (2014). Strokelets: A learned multi-scale representation for scene text recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4042\u20134049).","DOI":"10.1109\/CVPR.2014.515"},{"key":"1369_CR154","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., & Cao, Z. (2016). Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002."},{"issue":"7","key":"1369_CR155","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., & Doermann, D. (2015). Text detection and recognition in imagery: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(7), 1480\u20131500.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1369_CR156","unstructured":"Ye, Q., Gao, W., Wang, W., & Zeng, W. (2003). A robust text detection algorithm in images and video frames. In IEEE ICICS-PCM (pp. 802\u2013806)."},{"issue":"9","key":"1369_CR157","doi-asserted-by":"publisher","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 Transactions on Image Processing, 20(9), 2594\u20132605.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1369_CR158","unstructured":"Yin, F., Wu, Y.-C, Zhang, X.-Y., & Liu, C.-L. (2017). Scene text recognition with sliding convolutional character models. arXiv preprint arXiv:1709.01727."},{"issue":"5","key":"1369_CR159","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","volume":"36","author":"X-C Yin","year":"2014","unstructured":"Yin, X.-C., Yin, X., Huang, K., & Hao, H.-W. (2014). Robust text detection in natural scene images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 970\u2013983.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"1369_CR160","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"X-C Yin","year":"2016","unstructured":"Yin, X.-C., Zuo, Z.-Y., Tian, S., & Liu, C.-L. (2016). Text detection, tracking and recognition in video: A comprehensive survey. IEEE Transactions on Image Processing, 25(6), 2752\u20132773.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1369_CR161","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Han, J., Liu, J., & Ding, E. (2020). Towards accurate scene text recognition with semantic reasoning networks. arXiv preprint arXiv:2003.12294.","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"1369_CR162","unstructured":"Yuan, T.-L., Zhu, Z., Xu, K., Li, C.-J., & Hu, S.-M. (2018). Chinese text in the wild. arXiv preprint arXiv:1803.00085."},{"key":"1369_CR163","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 conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00216"},{"key":"1369_CR164","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S., & Xue, C. (2018). Verisimilar image synthesis for accurate detection and recognition of texts in scenes.","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"1369_CR165","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liang, B., Huang, Z., En, M., Han, J., Ding, E., & Ding, X. (2019). Look more than once: An accurate detector for text of arbitrary shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.01080"},{"key":"1369_CR166","doi-asserted-by":"crossref","unstructured":"Zhang, D., & Chang, S.-F. (2003). A Bayesian framework for fusing multiple word knowledge models in videotext recognition. In Computer vision and pattern recognition, 2003. IEEE.","DOI":"10.1109\/CVPR.2003.1211512"},{"key":"1369_CR167","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 AAAI, 2018.","DOI":"10.1609\/aaai.v32i1.11887"},{"key":"1369_CR168","doi-asserted-by":"crossref","unstructured":"Zhang, S.-X., Zhu, X., Hou, J.-B., Liu, C., Yang, C., Wang, H., & Yin, X.-C. (2020). Deep relational reasoning graph network for arbitrary shape text detection. arXiv preprint arXiv:2003.07493.","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"1369_CR169","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., & Bai, X. (2016). Multi-oriented text detection with fully convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.451"},{"key":"1369_CR170","doi-asserted-by":"crossref","unstructured":"Zhiwei, Z., Linlin, L., & Lim, T. C. (2010). Edge based binarization for video text images. In 2010 20th international conference on pattern recognition (ICPR) (pp. 133\u2013136). IEEE.","DOI":"10.1109\/ICPR.2010.41"},{"key":"1369_CR171","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., & Liang, J. (2017). EAST: An efficient and accurate scene text detector. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.283"},{"issue":"1","key":"1369_CR172","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., & Bai, X. (2016). Scene text detection and recognition: Recent advances and future trends. Frontiers of Computer Science, 10(1), 19\u201336.","journal-title":"Frontiers of Computer Science"},{"key":"1369_CR173","doi-asserted-by":"crossref","unstructured":"Zitnick, C. L., & Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In Proceedings of European conference on computer vision (ECCV) (pp. 391\u2013405). Springer.","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01369-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01369-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01369-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T13:22:16Z","timestamp":1723468936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01369-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,27]]},"references-count":173,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1369"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01369-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,27]]},"assertion":[{"value":"14 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}