{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:37:37Z","timestamp":1773513457311,"version":"3.50.1"},"reference-count":39,"publisher":"Tsinghua University Press","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s41095-021-0242-8","type":"journal-article","created":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T22:02:32Z","timestamp":1638741752000},"page":"273-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Scene text removal via cascaded text stroke detection and erasing"],"prefix":"10.26599","volume":"8","author":[{"given":"Xuewei","family":"Bian","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoqun","family":"Wang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weize","family":"Quan","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juntao","family":"Ye","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Beijing 100049, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"242_CR1","doi-asserted-by":"crossref","unstructured":"Wu, L.; Zhang, C. Q.; Liu, J. M.; Han, J. Y.; Liu, J. T.; Ding, E. R.; Bai, X. Editing text in the wild. In: Proceedings of the 27th ACM International Conference on Multimedia, 1500\u20131508, 2019.","DOI":"10.1145\/3343031.3350929"},{"key":"242_CR2","doi-asserted-by":"crossref","unstructured":"Khodadadi, M.; Behrad, A. Text localization, extraction and inpainting in color images. In: Proceedings of the 20th Iranian Conference on Electrical Engineering, 1035\u20131040, 2012.","DOI":"10.1109\/IranianCEE.2012.6292505"},{"issue":"2","key":"242_CR3","first-page":"930","volume":"2","author":"U Modha","year":"2012","unstructured":"Modha, U.; Dave, P. Image inpainting-automatic detection and removal of text from images. International Journal of Engineering Research and Applications Vol. 2, No. 2, 930\u2013932, 2012.","journal-title":"International Journal of Engineering Research and Applications"},{"key":"242_CR4","doi-asserted-by":"crossref","unstructured":"Wagh, P. D.; Patil, D. R. Text detection and removal from image using inpainting with smoothing. In: Proceedings of the International Conference on Pervasive Computing, 1\u20134, 2015.","DOI":"10.1109\/PERVASIVE.2015.7087154"},{"key":"242_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2014 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J.; Alahi, A.; Li, F. F. Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision \u2014 ECCV 2016. Lecture Notes in Computer Science, Vol. 9906. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 694\u2013711, 2016."},{"key":"242_CR6","doi-asserted-by":"crossref","unstructured":"Isola, P.; Zhu, J. Y.; Zhou, T. H.; Efros, A. A. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5967\u20135976, 2017.","DOI":"10.1109\/CVPR.2017.632"},{"key":"242_CR7","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y.; Park, T.; Isola, P.; Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2242\u20132251, 2017.","DOI":"10.1109\/ICCV.2017.244"},{"key":"242_CR8","doi-asserted-by":"crossref","unstructured":"Nakamura, T.; Zhu, A.; Yanai, K.; Uchida, S. Scene text eraser. In: Proceedings of the International Conference on Document Analysis and Recognition, 832\u2013837, 2017.","DOI":"10.1109\/ICDAR.2017.141"},{"key":"242_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, S.; Liu, Y.; Jin, L.; Huang, Y.; Lai, S. EnsNet: Ensconce text in the wild. In: Proceedings of the AAAI Conference on Artificial Intelligence, 801\u2013808, 2019.","DOI":"10.1609\/aaai.v33i01.3301801"},{"key":"242_CR10","doi-asserted-by":"crossref","unstructured":"Tursun, O.; Zeng, R.; Denman, S.; Sivapalan, S.; Sridharan, S.; Fookes, C. MTRNet: A generic scene text eraser. In: Proceedings of the International Conference on Document Analysis and Recognition, 2019.","DOI":"10.1109\/ICDAR.2019.00016"},{"key":"242_CR11","doi-asserted-by":"publisher","first-page":"103066","DOI":"10.1016\/j.cviu.2020.103066","volume":"201","author":"O Tursun","year":"2020","unstructured":"Tursun, O.; Denman, S.; Zeng, R.; Sivapalan, S.; Sridharan, S.; Fookes, C. MTRNet++: One-stage mask-based scene text eraser. Computer Vision and Image Understanding Vol. 201, 103066, 2020.","journal-title":"Computer Vision and Image Understanding"},{"key":"242_CR12","doi-asserted-by":"publisher","first-page":"8760","DOI":"10.1109\/TIP.2020.3018859","volume":"29","author":"C Y Liu","year":"2020","unstructured":"Liu, C. Y.; Liu, Y. L.; Jin, L. W.; Zhang, S. T.; Luo, C. J.; Wang, Y. P. EraseNet: End-to-end text removal in the wild. IEEE Transactions on Image Processing Vol. 29, 8760\u20138775, 2020.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"242_CR13","volume":"36","year":"2017","unstructured":"Iizuka, S.; Simo-Serra, E.; Ishikawa, H. Globally and locally consistent image completion. ACM Transactions on Graphics Vol. 36, No. 4, Article No. 107, 2017.","journal-title":"ACM Transactions on Graphics"},{"key":"242_CR14","doi-asserted-by":"crossref","unstructured":"Yu, J. H.; Lin, Z.; Yang, J. M.; Shen, X. H.; Lu, X.; Huang, T. S. Generative image inpainting with contextual attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5505\u20135514, 2018.","DOI":"10.1109\/CVPR.2018.00577"},{"issue":"7","key":"242_CR15","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q X Ye","year":"2015","unstructured":"Ye, Q. X.; Doermann, D. Text detection and recognition in imagery: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 37, No. 7, 1480\u20131500, 2015.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"242_CR16","doi-asserted-by":"crossref","unstructured":"Shi, B. G.; Bai, X.; Belongie, S. Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3482\u20133490, 2017.","DOI":"10.1109\/CVPR.2017.371"},{"key":"242_CR17","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y L Liu","year":"2019","unstructured":"Liu, Y. L.; Jin, L. W.; Zhang, S. T.; Luo, C. J.; Zhang, S. Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognition Vol. 90, 337\u2013345, 2019.","journal-title":"Pattern Recognition"},{"issue":"12","key":"242_CR18","doi-asserted-by":"publisher","first-page":"220103","DOI":"10.1007\/s11432-019-2673-8","volume":"62","author":"J Chen","year":"2019","unstructured":"Chen, J.; Lian, Z. H.; Wang, Y. Z.; Tang, Y. M.; Xiao, J. G. Irregular scene text detection via attention guided border labeling. Science China Information Sciences Vol. 62, No. 12, 220103, 2019.","journal-title":"Science China Information Sciences"},{"key":"242_CR19","doi-asserted-by":"publisher","first-page":"107026","DOI":"10.1016\/j.patcog.2019.107026","volume":"98","author":"W H He","year":"2020","unstructured":"He, W. H.; Zhang, X. Y.; Yin, F.; Luo, Z. B.; Ogier, J. M.; Liu, C. L. Realtime multi-scale scene text detection with scale-based region proposal network. Pattern Recognition Vol. 98, 107026, 2020.","journal-title":"Pattern Recognition"},{"key":"242_CR20","doi-asserted-by":"crossref","unstructured":"Baek, Y.; Lee, B.; Han, D.; Yun, S.; Lee, H. Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9357\u20139366, 2019.","DOI":"10.1109\/CVPR.2019.00959"},{"key":"242_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, C.; Yao, C.; Shi, B.; Bai, X. Automatic discrimination of text and non-text natural images. In: Proceedings of the 13th International Conference on Document Analysis and Recognition, 886\u2013890, 2015.","DOI":"10.1109\/ICDAR.2015.7333889"},{"issue":"10","key":"242_CR22","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.imavis.2004.02.006","volume":"22","author":"J Matas","year":"2004","unstructured":"Matas, J.; Chum, O.; Urban, M.; Pajdla, T. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing Vol. 22, No. 10, 761\u2013767, 2004.","journal-title":"Image and Vision Computing"},{"key":"242_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Machine Learning: ECML-98","author":"T Joachims","year":"1998","unstructured":"Joachims, T. Text categorization with Support Vector Machines: Learning with many relevant features. In: Machine Learning: ECML-98. Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence), Vol. 1398. Nedellec, C.; Rouveirol, C. Eds. Springer Berlin Heidelberg, 137\u2013142, 1998."},{"key":"242_CR24","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.patcog.2016.12.005","volume":"66","author":"X Bai","year":"2017","unstructured":"Bai, X.; Shi, B. G.; Zhang, C. Q.; Cai, X.; Qi, L. Text\/non-text image classification in the wild with convolutional neural networks. Pattern Recognition Vol. 66, 437\u2013446, 2017.","journal-title":"Pattern Recognition"},{"key":"242_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, M.; Wang, R.-Q.; Yin, F.; Zhang, X.-Y.; Huang, L.-L.; Ogier, J.-M. Fast text\/non-text image classification with knowledge distillation. In: Proceedings of the International Conference on Document Analysis and Recognition, 1458\u20131463, 2019.","DOI":"10.1109\/ICDAR.2019.00234"},{"key":"242_CR26","doi-asserted-by":"crossref","unstructured":"Gupta, N.; Jalal, A. S. Text or non-text image classification using fully convolution network (FCN). In: Proceedings of the International Conference on Contemporary Computing and Applications, 150\u2013153, 2020.","DOI":"10.1109\/IC3A48958.2020.233287"},{"key":"242_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, X.; Yao, C.; Wen, H.; Wang, Y.; Zhou, S.; He, W.; Liang, J. EAST: An efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2642\u20132651, 2017.","DOI":"10.1109\/CVPR.2017.283"},{"key":"242_CR28","doi-asserted-by":"crossref","unstructured":"Yu, J. H.; Lin, Z.; Yang, J. M.; Shen, X. H.; Lu, X.; Huang, T. Free-form image inpainting with gated convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 4470\u20134479, 2019.","DOI":"10.1109\/ICCV.2019.00457"},{"key":"242_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015. Lecture Notes in Computer Science, Vol. 9351. Navab, N.; Hornegger, J.; Wells, W.; Frangi, A. Eds. Springer Cham, 234\u2013241, 2015."},{"key":"242_CR30","unstructured":"Miyato, T.; Kataoka, T.; Koyama, M.; Yoshida, Y. Spectral normalization for generative adversarial networks. In: Proceedings of the International Conference on Learning Representations, 2018."},{"key":"242_CR31","unstructured":"Tran, D.; Ranganath, R.; Blei, D. Hierarchical implicit models and likelihood-free variational inference. In: Proceedings of the Advances in Neural Information Processing Systems, 5523\u20135533, 2017."},{"key":"242_CR32","unstructured":"Zhang, H.; Goodfellow, I.; Metaxas, D.; Odena, A. Self-attention generative adversarial networks. In: Proceedings of the 36th International Conference on Machine Learning, 7354\u20137363, 2019."},{"key":"242_CR33","doi-asserted-by":"crossref","unstructured":"Gatys, L. A.; Ecker, A. S.; Bethge, M. Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2414\u20132423, 2016.","DOI":"10.1109\/CVPR.2016.265"},{"issue":"10","key":"242_CR34","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.1109\/TIP.2005.851684","volume":"14","author":"H A Aly","year":"2005","unstructured":"Aly, H. A.; Dubois, E. Image up-sampling using total-variation regularization with a new observation model. IEEE Transactions on Image Processing Vol. 14, No. 10, 1647\u20131659, 2005.","journal-title":"IEEE Transactions on Image Processing"},{"key":"242_CR35","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, 2315\u20132324, 2016.","DOI":"10.1109\/CVPR.2016.254"},{"key":"242_CR36","doi-asserted-by":"crossref","unstructured":"Nayef, N.; Yin, F.; Bizid, I.; Choi, H.; Feng, Y.; Karatzas, D.; Luo, Z.; Pal, U.; Rigaud, C.; Chazalon, J. et al. ICDAR2017 robust reading challenge on multilingual scene text detection and script identification-RRC-MLT. In: Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, 1454\u20131459, 2017.","DOI":"10.1109\/ICDAR.2017.237"},{"key":"242_CR37","doi-asserted-by":"crossref","unstructured":"Dutta, A.; Zisserman, A. The VIA annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia, 2276\u20132279, 2019.","DOI":"10.1145\/3343031.3350535"},{"issue":"4","key":"242_CR38","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. Object count\/area graphs for the evaluation of object detection and segmentation algorithms. International Journal on Document Analysis and Recognition Vol. 8, No. 4, 280\u2013296, 2006.","journal-title":"International Journal on Document Analysis and Recognition"},{"key":"242_CR39","unstructured":"Kingma, D. P.; Ba, J. Adam: A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations, 2015."}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0242-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41095-021-0242-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-021-0242-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897476\/10897484.pdf?arnumber=10897484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:31Z","timestamp":1762367911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1007\/s41095-021-0242-8","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2022,6]]},"assertion":[{"value":"22 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}