{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:14:40Z","timestamp":1743117280815,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031090363"},{"type":"electronic","value":"9783031090370"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-09037-0_27","type":"book-chapter","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T04:26:16Z","timestamp":1654057576000},"page":"323-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scene Text Recognition: An Overview"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0595-4116","authenticated-orcid":false,"given":"Shiqi","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6296-9947","authenticated-orcid":false,"given":"Ning","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2281-5599","authenticated-orcid":false,"given":"Jun","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,2]]},"reference":[{"issue":"8","key":"27_CR1","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.: Textboxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process. 27(8), 3676\u20133690 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR2","doi-asserted-by":"publisher","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals.\u00a0IEEE Trans. Multimedia\u00a020(11), 3111\u20133122 (2018)","DOI":"10.1109\/TMM.2018.2818020"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Thirty-first AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In:\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2550\u20132558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"key":"27_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107684","volume":"111","author":"C Ma","year":"2021","unstructured":"Ma, C., Sun, L., Zhong, Z., Huo, Q.: ReLaText: exploiting visual relationships for arbitrary-shaped scene text detection with graph convolutional networks. Pattern Recogn. 111, 107684 (2021)","journal-title":"Pattern Recogn."},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Wang, X., Zheng, S., Zhang, C., Li, R., Gui, L.: R-YOLO: a real-time text detector for natural scenes with arbitrary rotation.\u00a0Sensors 21(3), 888 (2021)","DOI":"10.3390\/s21030888"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Xiao, L., Zhou, P., Xu, K., Zhao, X.: Multi-directional scene text detection based on improved YOLOv3.\u00a0Sensors\u00a021(14), 4870 (2021)","DOI":"10.3390\/s21144870"},{"key":"27_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-030-01216-8_2","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Long","year":"2018","unstructured":"Long, S., et al.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 19\u201335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_2"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Xie, E., et al.: Scene text detection with supervised pyramid context network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 9038\u20139045 (2019)","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Learning shape-aware embedding for scene text detection. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4234\u20134243 (2019)","DOI":"10.1109\/CVPR.2019.00436"},{"issue":"11","key":"27_CR15","doi-asserted-by":"publisher","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.: TextField: learning a deep direction field for irregular scene text detection. IEEE Trans. Image Process. 28(11), 5566\u20135579 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107336","volume":"110","author":"Y Zhu","year":"2021","unstructured":"Zhu, Y., Du, J.: Textmountain: accurate scene text detection via instance segmentation. Pattern Recogn. 110, 107336 (2021)","journal-title":"Pattern Recogn."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In:\u00a0Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"125184","DOI":"10.1109\/ACCESS.2021.3110858","volume":"9","author":"M Ghosh","year":"2021","unstructured":"Ghosh, M., et al.: Movie title extraction and script separation using shallow convolution neural network. IEEE Access 9, 125184\u2013125201 (2021)","journal-title":"IEEE Access"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Look more than once: an accurate detector for text of arbitrary shapes. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10552\u201310561 (2019)","DOI":"10.1109\/CVPR.2019.01080"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"He, M., et al.: MOST: a multi-oriented scene text detector with localization refinement. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8813\u20138822 (2021)","DOI":"10.1109\/CVPR46437.2021.00870"},{"issue":"11","key":"27_CR22","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: 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 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR23","unstructured":"Wang, J., Hu, X.: Gated recurrent convolution neural network for OCR. In:\u00a0Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 334\u2013343 (2017)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: STAR-Net: a spatial attention residue network for scene text recognition. In: BMVC, vol. 2, p. 7 (2016)","DOI":"10.5244\/C.30.43"},{"key":"27_CR25","first-page":"831","volume":"31","author":"H Liu","year":"2018","unstructured":"Liu, H., Jin, S., Zhang, C.: Connectionist temporal classification with maximum entropy regularization. Adv. Neural. Inf. Process. Syst. 31, 831\u2013841 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR26","unstructured":"Yin, F., Wu, Y.C., Zhang, X.Y., Liu, C.L.: Scene text recognition with sliding convolutional character models.\u00a0arXiv preprint arXiv:1709.01727(2017)"},{"key":"27_CR27","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.neucom.2019.01.094","volume":"339","author":"Y Gao","year":"2019","unstructured":"Gao, Y., Chen, Y., Wang, J., Tang, M., Lu, H.: Reading scene text with fully convolutional sequence modeling. Neurocomputing 339, 161\u2013170 (2019)","journal-title":"Neurocomputing"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In:\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"9","key":"27_CR29","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., et al.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR30","doi-asserted-by":"publisher","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.: MORAN: a multi-object rectified attention network for scene text recognition. Pattern Recognt. 90, 109\u2013118 (2019)","journal-title":"Pattern Recognt."},{"key":"27_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107692","volume":"111","author":"Q Lin","year":"2021","unstructured":"Lin, Q., Luo, C., Jin, L., Lai, S.: STAN: a sequential transformation attention-based network for scene text recognition. Pattern Recognt. 111, 107692 (2021)","journal-title":"Pattern Recognt."},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Cheng, Z., et al.: Focusing attention: towards accurate text recognition in natural images. In:\u00a0Proceedings of the IEEE International Conference on Computer Vision, pp. 5076\u20135084 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"27_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980","volume":"117","author":"N Lu","year":"2021","unstructured":"Lu, N., et al.: MASTER: multi-aspect non-local network for scene text recognition. Pattern Recognt. 117, 107980 (2021)","journal-title":"Pattern Recognt."},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Yan, R., Peng, L., Xiao, S., Yao, G.: Primitive representation learning for scene text recognition. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2021)","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Graph-based global reasoning networks. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 433\u2013442 (2019)","DOI":"10.1109\/CVPR.2019.00052"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Bhunia, A. K., et al.: Joint visual semantic reasoning: Multi-stage decoder for text recognition. In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14940\u201314949 (2021)","DOI":"10.1109\/ICCV48922.2021.01467"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Litman, R., et al.: SCATTER: selective context attentional scene text recognizer. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11962\u201311972 (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S.,  Lin, Z.: GTC: guided training of CTC towards efficient and accurate scene text recognition. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"27_CR42","doi-asserted-by":"publisher","unstructured":"Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds) ECCV 2018. LNCS, vol. 11218, pp. 67\u201383. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_5","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: FOTS: fast oriented text spotting with a unified network. In:\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Feng, W., He, W., Yin, F., Zhang, X.Y.,  Liu, C.L.: TextDragon: an end-to-end framework for arbitrary shaped text spotting. In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9076\u20139085 (2019)","DOI":"10.1109\/ICCV.2019.00917"},{"key":"27_CR45","unstructured":"Liao, M., et al.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. (2019)"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: All you need is boundary: toward arbitrary-shaped text spotting. In:\u00a0Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12160\u201312167 (2020)","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"27_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116512","volume":"100","author":"A Mittal","year":"2022","unstructured":"Mittal, A., Shivakumara, P., Pal, U., Lu, T., Blumenstein, M.: A new method for detection and prediction of occluded text in natural scene images. Signal Process. Image Commun. 100, 116512 (2022)","journal-title":"Signal Process. Image Commun."},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: ABCNet: real-time scene text spotting with adaptive Bezier-curve network. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: PGNet: real-time arbitrarily-shaped text spotting with point gathering network.\u00a0arXiv preprint arXiv:2104.05458(2021)","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: PAN++: towards efficient and accurate end-to-end spotting of arbitrarily-shaped text.\u00a0IEEE Trans. Pattern Anal. Machi. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3077555"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-09037-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T15:28:13Z","timestamp":1687879693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-09037-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031090363","9783031090370"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-09037-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"2 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icprai2022.sciencesconf.org\/1.6.If","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}