{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:19:16Z","timestamp":1755926356118,"version":"3.37.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030305079"},{"type":"electronic","value":"9783030305086"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30508-6_20","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:02:47Z","timestamp":1567969367000},"page":"238-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["COCO_TS Dataset: Pixel\u2013Level Annotations Based on Weak Supervision for Scene Text Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5540-3742","authenticated-orcid":false,"given":"Simone","family":"Bonechi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7790-6818","authenticated-orcid":false,"given":"Paolo","family":"Andreini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8206-8142","authenticated-orcid":false,"given":"Monica","family":"Bianchini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1307-0772","authenticated-orcid":false,"given":"Franco","family":"Scarselli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1484\u20131493. IEEE (2013). \n                      https:\/\/doi.org\/10.1109\/ICDAR.2013.221","key":"20_CR1","DOI":"10.1109\/ICDAR.2013.221"},{"doi-asserted-by":"publisher","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 935\u2013942 (2017). \n                      https:\/\/doi.org\/10.1109\/ICDAR.2017.157","key":"20_CR2","DOI":"10.1109\/ICDAR.2017.157"},{"issue":"3","key":"20_CR3","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1109\/TIP.2017.2656474","volume":"26","author":"Y Tang","year":"2017","unstructured":"Tang, Y., Wu, X.: Scene text detection and segmentation based on cascaded convolution neural networks. IEEE Trans. Image Process. 26(3), 1509\u20131520 (2017). \n                      https:\/\/doi.org\/10.1109\/TIP.2017.2656474","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"publisher","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition (2016). \n                      https:\/\/doi.org\/10.1109\/CVPR.2016.254","key":"20_CR4","DOI":"10.1109\/CVPR.2016.254"},{"unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint \n                      arXiv:1601.07140\n                      \n                     (2016). \n                      http:\/\/vision.cornell.edu\/se3\/wp-content\/uploads\/2016\/01\/1601.07140v1.pdf","key":"20_CR5"},{"doi-asserted-by":"publisher","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). \n                      https:\/\/doi.org\/10.1109\/ICDAR","key":"20_CR6","DOI":"10.1109\/ICDAR"},{"unstructured":"RRC-MLT: Mlt: Competition on multi-lingual scene text detection and script identification. \n                      http:\/\/rrc.cvc.uab.es\/?ch=8&com=introduction","key":"20_CR7"},{"key":"20_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/978-3-319-99978-4_15","volume-title":"Artificial Neural Networks in Pattern Recognition","author":"S Bonechi","year":"2018","unstructured":"Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F.: Generating bounding box supervision for semantic segmentation with deep learning. In: Pancioni, L., Schwenker, F., Trentin, E. (eds.) ANNPR 2018. LNCS (LNAI), vol. 11081, pp. 190\u2013200. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-319-99978-4_15"},{"doi-asserted-by":"publisher","unstructured":"Handa, A., Patraucean, V., Badrinarayanan, V., Stent, S., Cipolla, R.: Synthcam3d: Semantic understanding with synthetic indoor scenes. arXiv preprint \n                      arXiv:1505.00171\n                      \n                     (2015). \n                      https:\/\/doi.org\/10.17863\/CAM.26487","key":"20_CR9","DOI":"10.17863\/CAM.26487"},{"doi-asserted-by":"publisher","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3234\u20133243 (2016). \n                      https:\/\/doi.org\/10.1109\/CVPR.2016.352","key":"20_CR10","DOI":"10.1109\/CVPR.2016.352"},{"key":"20_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-01424-7_51","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"P Andreini","year":"2018","unstructured":"Andreini, P., Bonechi, S., Bianchini, M., Mecocci, A., Scarselli, F.: A deep learning approach to bacterial colony segmentation. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 522\u2013533. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01424-7_51"},{"issue":"1","key":"20_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"Max Jaderberg","year":"2015","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vis. 116(1), 1\u201320 (2016). \n                      https:\/\/doi.org\/10.1007\/s11263-015-0823-z","journal-title":"International Journal of Computer Vision"},{"doi-asserted-by":"publisher","unstructured":"Dai, J., He, K., Sun, J.: Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1635\u20131643 (2015). \n                      https:\/\/doi.org\/10.1109\/ICCV.2015.191","key":"20_CR13","DOI":"10.1109\/ICCV.2015.191"},{"doi-asserted-by":"publisher","unstructured":"Papandreou, G., Chen, L., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1742\u20131750. \n                      https:\/\/doi.org\/10.1109\/ICCV.2015.203","key":"20_CR14","DOI":"10.1109\/ICCV.2015.203"},{"doi-asserted-by":"publisher","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: weakly supervised instance and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 876\u2013885 (2017). \n                      https:\/\/doi.org\/10.1109\/CVPR.2017.181","key":"20_CR15","DOI":"10.1109\/CVPR.2017.181"},{"doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015). \n                      https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","key":"20_CR16","DOI":"10.1109\/CVPR.2015.7298965"},{"unstructured":"Papandreou, G., Kokkinos, I., Savalle, P.A.: Untangling local and global deformations in deep convolutional networks for image classification and sliding window detection. arXiv preprint \n                      arXiv:1412.0296\n                      \n                     (2014)","key":"20_CR17"},{"doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230\u20136239 (2017). \n                      https:\/\/doi.org\/10.1109\/CVPR.2017.660","key":"20_CR18","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"20_CR19","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"20_CR20","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62\u201366 (1979). \n                      https:\/\/doi.org\/10.1109\/TSMC.1979.4310076","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"3","key":"20_CR21","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.patcog.2005.09.010","volume":"39","author":"B. Gatos","year":"2006","unstructured":"Su, B., Lu, S., Tan, C.L.: Binarization of historical document images using the local maximum and minimum. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, pp. 159\u2013166. ACM (2010). \n                      https:\/\/doi.org\/10.1016\/j.patcog.2005.09.010","journal-title":"Pattern Recognition"},{"doi-asserted-by":"publisher","unstructured":"Howe, N.R.: A Laplacian energy for document binarization. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 6\u201310. IEEE (2011). \n                      https:\/\/doi.org\/10.1109\/ICDAR.2011.11","key":"20_CR22","DOI":"10.1109\/ICDAR.2011.11"},{"doi-asserted-by":"publisher","unstructured":"Bai, B., Yin, F., Liu, C.L.: A seed-based segmentation method for scene text extraction. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 262\u2013266. IEEE (2014). \n                      https:\/\/doi.org\/10.1109\/DAS.2014.34","key":"20_CR23","DOI":"10.1109\/DAS.2014.34"},{"doi-asserted-by":"publisher","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: An MRF model for binarization of natural scene text. In: ICDAR-International Conference on Document Analysis and Recognition. IEEE (2011). \n                      https:\/\/doi.org\/10.1109\/ICDAR.2011.12","key":"20_CR24","DOI":"10.1109\/ICDAR.2011.12"},{"doi-asserted-by":"publisher","unstructured":"Tian, S., Lu, S., Su, B., Tan, C.L.: Scene text segmentation with multi-level maximally stable extremal regions. In: 2014 22nd International Conference on Pattern Recognition (ICPR), pp. 2703\u20132708. IEEE (2014). \n                      https:\/\/doi.org\/10.1109\/ICPR.2014.467","key":"20_CR25","DOI":"10.1109\/ICPR.2014.467"},{"key":"20_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"publisher","unstructured":"Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 1491\u20131496. IEEE (2011). \n                      https:\/\/doi.org\/10.1109\/ICDAR.2011.296","key":"20_CR27","DOI":"10.1109\/ICDAR.2011.296"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint \n                      arXiv:1412.6980\n                      \n                     (2014)","key":"20_CR28"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Image Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30508-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:18:09Z","timestamp":1567970289000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30508-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030305079","9783030305086"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30508-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}