{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:42:38Z","timestamp":1777657358195,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863333","type":"print"},{"value":"9783030863340","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86334-0_17","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:16:02Z","timestamp":1630700162000},"page":"257-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A New Semi-automatic Annotation Model via Semantic Boundary Estimation for Scene Text Detection"],"prefix":"10.1007","author":[{"given":"Zhenzhou","family":"Zhuang","sequence":"first","affiliation":[]},{"given":"Zonghao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kin-Man","family":"Lam","sequence":"additional","affiliation":[]},{"given":"Shuangping","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Dai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"17_CR1","unstructured":"https:\/\/github.com\/PaddlePaddle\/PaddleOCR#"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Acuna, D., Ling, H., Kar, A., Fidler, S.: Efficient interactive annotation of segmentation datasets with polygon-RNN++. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 859\u2013868 (2018)","DOI":"10.1109\/CVPR.2018.00096"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: 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 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"17_CR4","unstructured":"Bartz, C., Bethge, J., Yang, H., Meinel, C.: Kiss: keeping it simple for scene text recognition. arXiv preprint arXiv:1911.08400 (2019)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in nd images. In: Proceedings Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 1, pp. 105\u2013112. IEEE (2001)","DOI":"10.1109\/ICCV.2001.937505"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a polygon-RNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5230\u20135238 (2017)","DOI":"10.1109\/CVPR.2017.477"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Tsai, S.S., Schroth, G., Chen, D.M., Grzeszczuk, R., Girod, B.: Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: 2011 18th IEEE International Conference on Image Processing, pp. 2609\u20132612. IEEE (2011)","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"17_CR8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10032-019-00334-z","volume":"23","author":"CK Ch\u2019ng","year":"2019","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: toward orientation robustiness in scene text detection. Int. J. Doc. Anal. Recogn. (IJDAR) 23, 31\u201352 (2019)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: Detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.neunet.2018.10.009","volume":"109","author":"Y Hu","year":"2019","unstructured":"Hu, Y., Soltoggio, A., Lock, R., Carter, S.: A fully convolutional two-stream fusion network for interactive image segmentation. Neural Netw. 109, 31\u201342 (2019)","journal-title":"Neural Netw."},{"key":"17_CR14","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Jang, W.D., Kim, C.S.: Interactive image segmentation via backpropagating refinement scheme. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297\u20135306 (2019)","DOI":"10.1109\/CVPR.2019.00544"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., G\u00f3mez, L., Nicolaou, A., Rusinol, M.: The robust reading competition annotation and evaluation platform. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 61\u201366. IEEE (2018)","DOI":"10.1109\/DAS.2018.22"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Q., Koltun, V.: Interactive image segmentation with latent diversity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 577\u2013585 (2018)","DOI":"10.1109\/CVPR.2018.00067"},{"issue":"8","key":"17_CR19","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":"17_CR20","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Liew, J., Wei, Y., Xiong, W., Ong, S.H., Feng, J.: Regional interactive image segmentation networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2746\u20132754. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.297"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhang, Z., Chen, L.Z., Cheng, M.M., Lu, S.P.: Interactive image segmentation with first click attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13339\u201313348 (2020)","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Ling, H., Gao, J., Kar, A., Chen, W., Fidler, S.: Fast interactive object annotation with curve-GCN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5257\u20135266 (2019)","DOI":"10.1109\/CVPR.2019.00540"},{"issue":"2","key":"17_CR24","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s10032-019-00320-5","volume":"22","author":"X Liu","year":"2019","unstructured":"Liu, X., Meng, G., Pan, C.: Scene text detection and recognition with advances in deep learning: a survey. Int. J. Doc. Anal. Recogn. (IJDAR) 22(2), 143\u2013162 (2019). https:\/\/doi.org\/10.1007\/s10032-019-00320-5","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: ABCNet: real-time scene text spotting with adaptive Bezier-curve network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9809\u20139818 (2020)","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"17_CR26","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337\u2013345 (2019)","journal-title":"Pattern Recogn."},{"key":"17_CR27","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2020","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vis. 129, 161\u2013184 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"17_CR29","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 Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Papadopoulos, D.P., Uijlings, J.R., Keller, F., Ferrari, V.: Extreme clicking for efficient object annotation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4930\u20134939 (2017)","DOI":"10.1109\/ICCV.2017.528"},{"key":"17_CR31","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s41095-020-0177-5","volume":"6","author":"H Ramadan","year":"2020","unstructured":"Ramadan, H., Lachqar, C., Tairi, H.: A survey of recent interactive image segmentation methods. Comput. Vis. Media 6, 355\u2013384 (2020)","journal-title":"Comput. Vis. Media"},{"issue":"3","key":"17_CR32","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cGrabCut\u2019\u2019 interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309\u2013314 (2004)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"17_CR33","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2019","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2035\u20132048 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Tang, M., Gorelick, L., Veksler, O., Boykov, Y.: GrabCut in one cut. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1769\u20131776 (2013)","DOI":"10.1109\/ICCV.2013.222"},{"key":"17_CR35","unstructured":"Tzutalin: Labelimg. https:\/\/github.com\/tzutalin\/labelImg#"},{"key":"17_CR36","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":"17_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Jiang, Y., Luo, Z., Liu, C.L., Choi, H., Kim, S.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00661"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z.J., Xing, M., Fu, Z., Zhang, Y.: ContourNet: taking a further step toward accurate arbitrary-shaped scene text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11753\u201311762 (2020)","DOI":"10.1109\/CVPR42600.2020.01177"},{"issue":"1","key":"17_CR39","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1111\/1467-9868.00374","volume":"65","author":"SN Wood","year":"2003","unstructured":"Wood, S.N.: Thin plate regression splines. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 65(1), 95\u2013114 (2003)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"17_CR40","first-page":"3871897","volume":"2020","author":"W Wu","year":"2020","unstructured":"Wu, W., Xing, J., Yang, C., Wang, Y., Zhou, H.: Texts as lines: text detection with weak supervision. Math. Probl. Eng. 2020, 3871897 (2020)","journal-title":"Math. Probl. Eng."},{"issue":"11","key":"17_CR41","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":"17_CR42","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: End-to-end scene text recognition via iterative image rectification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2059\u20132068 (2019)","DOI":"10.1109\/CVPR.2019.00216"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Look more than once: An accurate detector for text of arbitrary shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10552\u201310561 (2019)","DOI":"10.1109\/CVPR.2019.01080"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liew, J.H., Wei, Y., Wei, S., Zhao, Y.: Interactive object segmentation with inside-outside guidance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12234\u201312244 (2020)","DOI":"10.1109\/CVPR42600.2020.01225"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, W., Qiu, Y., Liao, M., Zhang, R., Wei, X., Bai, X.: Scene text detection with scribble lines. arXiv preprint arXiv:2012.05030 (2020)","DOI":"10.1007\/978-3-030-86337-1_6"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"17_CR47","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jvcir.2015.10.012","volume":"34","author":"H Zhu","year":"2016","unstructured":"Zhu, H., Meng, F., Cai, J., Lu, S.: Beyond pixels: a comprehensive survey from bottom-up to semantic image segmentation and cosegmentation. J. Vis. Commun. Image Representation 34, 12\u201327 (2016)","journal-title":"J. Vis. Commun. Image Representation"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86334-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:03:48Z","timestamp":1756850628000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86334-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863333","9783030863340"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86334-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"182","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}