{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:10:21Z","timestamp":1766067021264},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T00:00:00Z","timestamp":1559606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T00:00:00Z","timestamp":1559606400000},"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\/s10032-019-00326-z","type":"journal-article","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T17:02:26Z","timestamp":1559667746000},"page":"209-219","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Boosting scene character recognition by learning canonical forms of glyphs"],"prefix":"10.1007","volume":"22","author":[{"given":"Yizhi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhouhui","family":"Lian","sequence":"additional","affiliation":[]},{"given":"Yingmin","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Jianguo","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,4]]},"reference":[{"key":"326_CR1","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: Photoocr: reading text in uncontrolled conditions. In: IEEE International Conference on Computer Vision, pp. 785\u2013792 (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"326_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5086\u20135094 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"326_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: Aon: towards arbitrarily-oriented text recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5571\u20135579 (2018)","DOI":"10.1109\/CVPR.2018.00584"},{"key":"326_CR4","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886\u2013893 (2005)"},{"key":"326_CR5","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 248\u2013255 (2009)"},{"key":"326_CR6","unstructured":"Denton, E.L., Chintala, S., Szlam, A., Fergus, R.: Deep generative image models using a laplacian pyramid of adversarial networks. In: Neural Information Processing Systems, pp. 1486\u20131494 (2015)"},{"key":"326_CR7","first-page":"2672","volume":"3","author":"IJ Goodfellow","year":"2014","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Adv. Neural Inf. Process. Syst. 3, 2672\u20132680 (2014)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"326_CR8","unstructured":"Google: Tesseract optical character recognition. https:\/\/code.google.com\/p\/tesseract-ocr\/ (2006)"},{"key":"326_CR9","unstructured":"Google: Tensorflow. https:\/\/www.tensorflow.org\/ (2016)"},{"key":"326_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"326_CR11","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967\u20135976 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"326_CR12","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Deep structured output learning for unconstrained text recognition. In: International Conference on Learning Representations (2015)"},{"issue":"1","key":"326_CR13","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. Int. J. Comput. Vis. 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"326_CR14","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: European Conference on Computer Vision, pp. 512\u2013528 (2014)","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"326_CR15","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almaz\u00e0n, J.A., de las Heras, L.P.: Icdar 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"326_CR16","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"326_CR17","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for ocr in the wild. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"issue":"2\u20133","key":"326_CR18","first-page":"105","volume":"7","author":"SM Lucas","year":"2003","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. Proc ICDAR 7(2\u20133), 105\u2013122 (2003)","journal-title":"Proc ICDAR"},{"key":"326_CR19","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar,C.V.: Scene text recognition using higher order language priors. In: British machine vision conference, pp. 127.1\u2013127.11 (2012)","DOI":"10.5244\/C.26.127"},{"key":"326_CR20","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: International conference on learning representations (2016)"},{"key":"326_CR21","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"11","key":"326_CR22","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"326_CR23","doi-asserted-by":"crossref","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. 1 (2018)","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"326_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"issue":"C","key":"326_CR25","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.patcog.2015.07.009","volume":"51","author":"S Tian","year":"2016","unstructured":"Tian, S., Bhattacharya, U., Lu, S., Su, B., Wang, Q., Wei, X., Lu, Y., Tan, C.L.: Multilingual scene character recognition with co-occurrence of histogram of oriented gradients. Pattern Recognit. 51(C), 125\u2013134 (2016)","journal-title":"Pattern Recognit."},{"key":"326_CR26","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: International Conference on Pattern Recognition, pp. 3304\u20133308 (2013)"},{"key":"326_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shi, C., Xiao, B., Wang, C.: Learning spatially embedded discriminative part detectors for scene character recognition. In: IAPR International Conference on Document Analysis and Recognition, pp. 363\u2013368 (2017)","DOI":"10.1109\/ICDAR.2017.67"},{"key":"326_CR28","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818\u2013833 (2014)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"326_CR29","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.patrec.2018.02.006","volume":"106","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Liang, S., Nie, S., Liu, W., Peng, S.: Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data. Pattern Recognit. Lett. 106, 20\u201326 (2018)","journal-title":"Pattern Recognit. Lett."},{"key":"326_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, Y., Liu, C.L.: Natural scene character recognition using robust PCA and sparse representation. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), pp. 340\u2013345. IEEE (2016)","DOI":"10.1109\/DAS.2016.32"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00326-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-019-00326-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00326-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T12:48:37Z","timestamp":1663591717000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-019-00326-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,4]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["326"],"URL":"https:\/\/doi.org\/10.1007\/s10032-019-00326-z","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,4]]},"assertion":[{"value":"14 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}