{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T14:55:29Z","timestamp":1778079329663,"version":"3.51.4"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T00:00:00Z","timestamp":1565222400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T00:00:00Z","timestamp":1565222400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703316"],"award-info":[{"award-number":["61703316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key RD Program of China","award":["2017YFB1402200"],"award-info":[{"award-number":["2017YFB1402200"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10032-019-00341-0","type":"journal-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T06:02:33Z","timestamp":1565244153000},"page":"351-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Coarse-to-fine document localization in natural scene image with regional attention and recursive corner refinement"],"prefix":"10.1007","volume":"22","author":[{"given":"Anna","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhi","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3931-9687","authenticated-orcid":false,"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,8]]},"reference":[{"key":"341_CR1","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"341_CR2","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., Li, X.: Single shot text detector with regional attention. In: IEEE International Conference on Computer Vision, pp. 3047\u20133055 (2017)","DOI":"10.1109\/ICCV.2017.331"},{"key":"341_CR3","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceeding of International Conference on Computer Vision, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"341_CR4","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1016\/j.patcog.2006.04.027","volume":"40","author":"Y Qiao","year":"2007","unstructured":"Qiao, Y., Hu, Q.M., Qian, G.Y., Luo, S.H., Nowinski, W.L.: Thresholding based on variance and intensity contrast. Pattern Recognit. 40, 596\u2013608 (2007)","journal-title":"Pattern Recognit."},{"key":"341_CR5","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1109\/TIP.2002.806231","volume":"11","author":"OJ Tobias","year":"2002","unstructured":"Tobias, O.J., Seara, R.: Image segmentation by histogram thresholding using fuzzy sets. IEEE Trans. Image Process. 11, 1457\u201365 (2002)","journal-title":"IEEE Trans. Image Process."},{"key":"341_CR6","unstructured":"Lampert, C.H., Braun, T., Ulges, A., Keysers, D., Breuel, T.M.: Oblivious document capture and real-time retrieval. In: Proceeding of International Conference on Camera Based Document Analysis and Recognition, pp. 79\u201386 (2005)"},{"key":"341_CR7","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/PL00013394","volume":"16","author":"E Guillou","year":"2000","unstructured":"Guillou, E., Meneveaux, D., Maisel, E., Bouaouch, K.: Using vanishing points for camera calibration and coarse 3D reconstruction from a single image. Visual Comput. 16, 396\u2013410 (2000)","journal-title":"Visual Comput."},{"key":"341_CR8","unstructured":"Kofler, C., Keysers, D., Koetsier, A., Laagland, J., Breuel, T.M.: Gestural interaction for an automatic document capture system. In: Proceedings of the International Workshop on Camera-Based Document Analysis and Recognition, pp. 161\u2013167 (2007)"},{"key":"341_CR9","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1016\/S0031-3203(03)00132-8","volume":"36","author":"P Clark","year":"2003","unstructured":"Clark, P., Mirmehdi, M.: Rectifying perspective view of text in 3D scenes using vanishing points. Pattern Recognit. 36, 2673\u20132686 (2003)","journal-title":"Pattern Recognit."},{"key":"341_CR10","unstructured":"Miao, L., Peng, S.: Perspective rectification of document images based on morphology. In: International Conference on Computational Intelligence and Security, pp. 1805\u20131808 (2009)"},{"key":"341_CR11","doi-asserted-by":"crossref","unstructured":"Lu, S., Tan, C.L.: The restoration of camera documents through image segmentation. In: Proceeding of Document Analysis Systems, vol. 3872, pp. 484\u2013495 (2006)","DOI":"10.1007\/11669487_43"},{"key":"341_CR12","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/j.imavis.2005.01.003","volume":"23","author":"S Lu","year":"2005","unstructured":"Lu, S., Chen, B.M., Ko, C.C.: Perspective rectification of document images using fuzzy set and morphological operations. Image Vis. Comput. 23, 541\u2013553 (2005)","journal-title":"Image Vis. Comput."},{"key":"341_CR13","first-page":"597","volume":"182","author":"N Stamatopoulos","year":"2007","unstructured":"Stamatopoulos, N., Gatos, B., Kesidis, A.: Automatic borders detection of camera document images. Psychopharmacology 182, 597\u2013598 (2007)","journal-title":"Psychopharmacology"},{"key":"341_CR14","doi-asserted-by":"crossref","unstructured":"Bulatov, K., Arlazarov, V.V., Chernov, T., Slavin, O., Nikolaev, D.: Smart IDReader: document recognition in video stream. In: Proceeding of International Conference on Document Analysis and Recognition, pp. 39\u201344 (2018)","DOI":"10.1109\/ICDAR.2017.347"},{"key":"341_CR15","unstructured":"Zhang, Z., He, L. W.: Note-taking with a camera: whiteboard scanning and image enhancement. In: Proceeding of International Conference on Acoustics, Speech, and Signal Processing, pp. 533\u2013536 (2004)"},{"key":"341_CR16","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 3476\u20133483 (2013)","DOI":"10.1109\/CVPR.2013.446"},{"key":"341_CR17","doi-asserted-by":"crossref","unstructured":"Zhukovsky, A., Nikolaev, D., Arlazarov, V., Postnikov, V., Polevoy, D., Skoryukina, N., Chernov, T., Shemiakina, J., Mukovozov, A., Konovalenko, I.: Segments graph-based approach for document capture in a smartphone video stream. In: Proceeding of International Conference on Document Analysis and Recognition, pp. 337\u2013342 (2018)","DOI":"10.1109\/ICDAR.2017.63"},{"key":"341_CR18","doi-asserted-by":"crossref","unstructured":"Javed, K., Shafait, F.: Real-time document localization in natural images by recursive application of a CNN. In: Proceeding of International Conference on Document Analysis and Recognition, pp. 105\u2013110 (2017)","DOI":"10.1109\/ICDAR.2017.26"},{"key":"341_CR19","doi-asserted-by":"crossref","unstructured":"Yin, X.C., Sun, J., Naoi, S., Fujimoto, K., Fujii, Y., Kurokawa, K., Takebe, H.: A multi-stage strategy to perspective rectification for mobile phone camera-based document images. In: Proceeding of International Conference on Document Analysis and Recognition, pp. 574\u2013578 (2007)","DOI":"10.1109\/ICDAR.2007.4376980"},{"key":"341_CR20","unstructured":"Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations (2018). arXiv preprint arXiv: 1805.12177"},{"key":"341_CR21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI Conference on Artificial Intelligence, pp. 4278\u20134284 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"341_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"341_CR23","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. In: USENIX Symposium on Operating Systems Design and Implementation, pp. 265\u2013283 (2016)"},{"key":"341_CR24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceeding of International Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"341_CR25","doi-asserted-by":"crossref","unstructured":"Burie, J.C., Chazalon, J., Coustaty, M., Eskenazi, S., Luqman, M.M., Mehri, M., Nayef, N., Ogier, J.M., Prum, S., Rusinol, M.: ICDAR2015 competition on smartphone document capture and OCR (Smart-Doc). In: Proceeding of International Conference on Document Analysis and Recognition, pp. 1161\u20131165 (2015)","DOI":"10.1109\/ICDAR.2015.7333943"},{"key":"341_CR26","doi-asserted-by":"crossref","unstructured":"Zisserman, A.: The Pascal Visual Object Classes Challenge. Lecture Notes in Computer Science, vol. 111, pp. 98\u2013136 (2007)","DOI":"10.1007\/s11263-014-0733-5"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00341-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-019-00341-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00341-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T08:58:28Z","timestamp":1664096308000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-019-00341-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,8]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["341"],"URL":"https:\/\/doi.org\/10.1007\/s10032-019-00341-0","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,8]]},"assertion":[{"value":"15 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}