{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T12:45:20Z","timestamp":1769085920085,"version":"3.49.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10032-019-00335-y","type":"journal-article","created":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T09:03:07Z","timestamp":1564045387000},"page":"315-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":105,"title":["An anchor-free region proposal network for Faster R-CNN-based text detection approaches"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9210-811X","authenticated-orcid":false,"given":"Zhuoyao","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Huo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"335_CR1","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: ICDAR, pp. 1491\u20131496 (2011)","DOI":"10.1109\/ICDAR.2011.296"},{"key":"335_CR2","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., Gomez, L., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., de las Heras, L.P.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"335_CR3","unstructured":"Karatzas, D., Gomez, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S.-J., Shafait, F., Uchida, S., Valveny, E.: ICDAR 2015 robust reading competition. In: ICDAR, pp. 1156\u20131160 (2015)"},{"key":"335_CR4","doi-asserted-by":"crossref","unstructured":"Nayef, N., Yin, F., Bizid, I., Choi, H., Feng, Y., Karatzas, D., Luo, Z.-B., Pal, U., Rigaud, C., Chazalon, J., Khlif, W., Luqman, M.M., Burie, J.C., Liu, C.-L., Ogier, J.M.: ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification\u2014RRC-MLT. In: ICDAR, pp. 1454\u20131459 (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"issue":"6","key":"335_CR5","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S-Q Ren","year":"2017","unstructured":"Ren, S.-Q., He, K.-M., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. PAMI 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. PAMI"},{"key":"335_CR6","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: Single shot multiBox detector. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"335_CR7","doi-asserted-by":"crossref","unstructured":"Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, pp. 384\u2013393 (2002)","DOI":"10.5244\/C.16.36"},{"key":"335_CR8","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR, pp. 2963\u20132970 (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"335_CR9","doi-asserted-by":"crossref","unstructured":"He, W.-H., Zhang, X.-Y., Yin, F., Liu, C.-L.: Deep direct regression for multi-oriented scene text detection. In: ICCV, pp. 745\u2013753 (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"335_CR10","doi-asserted-by":"crossref","unstructured":"Zhong, Z.-Y., Jin, L.-W., Huang, S.-P.: DeepText: a new approach for proposal generation and text detection in natural images. In: ICASSP, pp. 1208\u20131212 (2017)","DOI":"10.1109\/ICASSP.2017.7952348"},{"key":"335_CR11","doi-asserted-by":"crossref","unstructured":"Liao, M.-H., Shi, B.-G., Bai, X., Wang, X.-G., Liu, W.-Y.: TextBoxes: a fast text detector with a single deep neural network. In: AAAI, pp. 4164\u20134167 (2016)","DOI":"10.1609\/aaai.v31i1.11196"},{"issue":"11","key":"335_CR12","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J-Q Ma","year":"2018","unstructured":"Ma, J.-Q., Shao, W.-Y., Ye, H., Wang, L., Wang, H., Zheng, Y.-B., Xue, X.-Y.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimed. 20(11), 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"335_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y.-L., Jin, L.-W.: Deep matching prior network toward tighter multi-oriented text detection. In: CVPR, pp. 1962\u20131969 (2017)","DOI":"10.1109\/CVPR.2017.368"},{"key":"335_CR14","unstructured":"Huang, L.-C., Yang, Y., Deng, T.-F., Yu, Y.-N.: Densebox: unifying landmark localization with end to end object detection. Preprint (2015). arXiv:1509.04874"},{"key":"335_CR15","doi-asserted-by":"crossref","unstructured":"Zhou, X.-Y., Yao, C., Wen, H., Wang, Y.-Z., Zhou, S.-C., He, W.-R., Liang, J.-J.: EAST: An efficient and accurate scene text detector. In: CVPR, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"issue":"4","key":"335_CR16","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"J Long","year":"2017","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. PAMI 39(4), 640\u2013651 (2017)","journal-title":"IEEE Trans. PAMI"},{"key":"335_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R.B., He, K.-M., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"335_CR18","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: COCO-Text: dataset and benchmark for text detection and recognition in natural images. Preprint (2016). arXiv:1601.07140"},{"key":"335_CR19","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: ACCV, pp. 770\u2013783 (2010)","DOI":"10.1007\/978-3-642-19318-7_60"},{"key":"335_CR20","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR, pp. 3538\u20133545 (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"issue":"5","key":"335_CR21","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.-W., Huang, K.-Z., Hao, H.-W.: Robust text detection in natural scene images. IEEE Trans. PAMI 36(5), 970\u2013983 (2014)","journal-title":"IEEE Trans. PAMI"},{"key":"335_CR22","doi-asserted-by":"crossref","unstructured":"Huang, W.-L., Qiao, Y., Tang, X.-O.: Robust scene text detection with convolutional neural networks induced MSER trees. In: ECCV, pp. 497\u2013511 (2014)","DOI":"10.1007\/978-3-319-10593-2_33"},{"issue":"9","key":"335_CR23","doi-asserted-by":"publisher","first-page":"2906","DOI":"10.1016\/j.patcog.2015.04.002","volume":"48","author":"L Sun","year":"2015","unstructured":"Sun, L., Huo, Q., Jia, W., Chen, K.: A robust approach for text detection from natural scene images. Pattern Recogn. 48(9), 2906\u20132920 (2015)","journal-title":"Pattern Recogn."},{"issue":"9","key":"335_CR24","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"X-C Yin","year":"2015","unstructured":"Yin, X.-C., Pei, W.-Y., Zhang, J., Hao, H.-W.: Multi-orientation scene text detection with adaptive clustering. IEEE Trans. PAMI 37(9), 1930\u20131937 (2015)","journal-title":"IEEE Trans. PAMI"},{"issue":"2","key":"335_CR25","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10032-015-0237-z","volume":"18","author":"S-J Lu","year":"2015","unstructured":"Lu, S.-J., Chen, T., Tian, S.-X., Lim, J.-H., Tan, C.-L.: Scene text extraction based on edges and support vector regression. IJDAR 18(2), 125\u2013135 (2015)","journal-title":"IJDAR"},{"issue":"4","key":"335_CR26","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10032-016-0274-2","volume":"19","author":"L Gomez","year":"2016","unstructured":"Gomez, L., Karatzas, D.: A fast hierarchical method for multi-script and arbitrary oriented scene text extraction. IJDAR 19(4), 335\u2013349 (2016)","journal-title":"IJDAR"},{"issue":"2","key":"335_CR27","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10032-016-0264-4","volume":"19","author":"J Fabrizio","year":"2016","unstructured":"Fabrizio, J., Robert-Seidowsky, M., Dubuisson, S., Calarasanu, S., Boissel, R.: TextCatcher: a method to detect curved and challenging text in natural scenes. IJDAR 19(2), 99\u2013117 (2016)","journal-title":"IJDAR"},{"key":"335_CR28","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2017.04.027","volume":"70","author":"L Gomez","year":"2017","unstructured":"Gomez, L., Karatzas, D.: TextProposals: a text-specific selective search algorithm for word spotting in the wild. Pattern Recogn. 70, 60\u201374 (2017)","journal-title":"Pattern Recogn."},{"key":"335_CR29","unstructured":"Wang, T., Wu, D.-J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: ICPR, pp. 3304\u20133308 (2012)"},{"key":"335_CR30","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: ECCV, pp. 512\u2013528 (2014)","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"335_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: CVPR, pp. 4159\u20134167 (2016)","DOI":"10.1109\/CVPR.2016.451"},{"key":"335_CR32","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X.-Y., Zhou, S.-C., Cao, Z.-M.: Scene text detection via holistic, multi-channel prediction. Preprint (2016). arXiv:1606.09002"},{"issue":"1","key":"335_CR33","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.: Reading text in the wild with convolutional neural networks. IJCV 116(1), 1\u201320 (2016)","journal-title":"IJCV"},{"key":"335_CR34","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localization in natural images. In: CVPR, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"335_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W.-L., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: ECCV, pp. 56\u201372 (2016)","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"335_CR36","doi-asserted-by":"crossref","unstructured":"Shi, B.-G., Bai, X., Belongiey, S.: Detecting oriented text in natural images by linking segments. In: CVPR, pp. 2550\u20132558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"key":"335_CR37","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C.-Q., Luo, Y.-X., Wang, Y.-Z., Han, J.-Y., Ding, E.: WordSup: exploiting word annotations for character based text detection. In: ICCV, pp. 4940\u20134949 (2017)","DOI":"10.1109\/ICCV.2017.529"},{"issue":"5","key":"335_CR38","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., Jain, A.: Text information extraction in images and video: a survey. Pattern Recogn. 37(5), 977\u2013997 (2004)","journal-title":"Pattern Recogn."},{"issue":"3","key":"335_CR39","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s10032-018-0304-3","volume":"21","author":"G Renton","year":"2018","unstructured":"Renton, G., Soullard, Y., Chatelain, C., Adam, S., Kermorvant, C., Paquet, T.: Fully convolutional network with dilated convolutions for handwritten text line segmentation. IJDAR 21(3), 177\u2013186 (2018)","journal-title":"IJDAR"},{"key":"335_CR40","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"335_CR41","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"335_CR42","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H.-F., Li, X.-L., Cai, D.: Pixellink: detecting scene text via instance segmentation. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"335_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R.B., He, K.-M., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"335_CR44","doi-asserted-by":"crossref","unstructured":"He, K.-M., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"335_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"335_CR46","doi-asserted-by":"crossref","unstructured":"He, K.-M., Zhang, X.-Y., Ren, S.-Q., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"335_CR47","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"335_CR48","doi-asserted-by":"crossref","unstructured":"Gomez, R., Shi, B.-G., Gomez, L., Neumann, L., Veit, A., Matas, J., Belongie, S., Karatzas, D.: ICDAR2017 robust reading challenge on COCO-Text. In: ICDAR, pp. 1435\u20131443 (2017)","DOI":"10.1109\/ICDAR.2017.234"},{"key":"335_CR49","doi-asserted-by":"crossref","unstructured":"Liu, X.-B., Liang, D., Yan, S., Chen, D.-G., Qiao, Y., Yan, J.-J.: FOTS: fast oriented text spotting with a unified network. In: CVPR, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"335_CR50","unstructured":"Girshick, R.B., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.-M.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"335_CR51","doi-asserted-by":"crossref","unstructured":"Lyu, P.-Y., Yao, C., Wu, W.-H., Yan, S.-C., Bai, X.: Multi-Oriented scene text detection via corner localization and region segmentation. In: CVPR, pp. 7553\u20137563 (2018)","DOI":"10.1109\/CVPR.2018.00788"},{"key":"335_CR52","doi-asserted-by":"crossref","unstructured":"Liao, M.-H., Zhu, Z., Shi, B.-G., Xia, G.-S., Bai, X.: Rotation-sensitive regression for oriented scene text detection. In: CVPR, pp. 5909\u20135918 (2018)","DOI":"10.1109\/CVPR.2018.00619"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00335-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-019-00335-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00335-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T15:03:58Z","timestamp":1664031838000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-019-00335-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["335"],"URL":"https:\/\/doi.org\/10.1007\/s10032-019-00335-y","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"14 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}