{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:57:18Z","timestamp":1757311038039,"version":"3.41.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319219684"},{"type":"electronic","value":"9783319219691"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-21969-1_27","type":"book-chapter","created":{"date-parts":[[2015,8,3]],"date-time":"2015-08-03T08:48:26Z","timestamp":1438591706000},"page":"310-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Scene Character and Text Recognition: The State-of-the-Art"],"prefix":"10.1007","author":[{"given":"Chongmu","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da-Han","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"7","key":"27_CR1","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey, IEEE. Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"27_CR2","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.I., Jain, A.K.: Text information extraction in images and video: a survey. Pattern Recognit. 37(5), 977\u2013997 (2004)","journal-title":"Pattern Recognit."},{"issue":"2\u20133","key":"27_CR3","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/s10032-004-0138-z","volume":"7","author":"J Liang","year":"2005","unstructured":"Liang, J., Doermann, D., Li, H.: Camera-based analysis of text and documents: a survey. Int. J. Doc. Anal. Recognit. 7(2\u20133), 84\u2013104 (2005)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.neucom.2013.05.037","volume":"122","author":"H Zhang","year":"2013","unstructured":"Zhang, H., Zhao, K., Song, Y.-Z., Guo, J.: Text extraction from natural scene image: a survey. Neurocomputing 122, 310\u2013323 (2013)","journal-title":"Neurocomputing"},{"unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. In: Proceedings of International Conference on Document Analysis and Recognition (2003)","key":"27_CR5"},{"doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: Proceedings ICDAR, pp. 1491\u20131496 (2011)","key":"27_CR6","DOI":"10.1109\/ICDAR.2011.296"},{"unstructured":"de Campos, T.E., Babu, B.R., Varma, M.: Character recognition in natural images. In: Proceedings of International Conference on Computer Vision Theory and Applications, Lisbon (2009)","key":"27_CR7"},{"unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: Proceedings ICCV, pp. 1457\u20131464 (2011)","key":"27_CR8"},{"doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: Scene text recognition using higher order language priors. In: Proceedings BMVC, pp. 1\u201311 (2012)","key":"27_CR9","DOI":"10.5244\/C.26.127"},{"doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., Liu, W.: Strokelets: a learned multi-scale representation for scene text recognition. In: Proceedings CVPR (2014)","key":"27_CR10","DOI":"10.1109\/CVPR.2014.515"},{"unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: Proceedings ICPR, pp. 3304\u20133308 (2012)","key":"27_CR11"},{"key":"27_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/978-3-319-10593-2_34","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 512\u2013528. Springer, Heidelberg (2014)"},{"unstructured":"Alsharif, O., Pineau, J.: End-to-end text recognition with hybrid HMM maxout models. In: International Conference on Learning Representations (2014)","key":"27_CR13"},{"doi-asserted-by":"crossref","unstructured":"Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T., Wu, D.J., Ng, A.Y.: Text detection and character recognition in scene images with unsupervised feature learning. In: Proceedings ICDAR, pp. 440\u2013445 (2011)","key":"27_CR14","DOI":"10.1109\/ICDAR.2011.95"},{"doi-asserted-by":"crossref","unstructured":"Su, B., Lu, S., Tian, S. , Lim, J.-H., Tan, C.L.: Character recognition in natural scenes using convolutional co-occurrence HOG. In: Proceedings ICPR, pp. 2926\u20132931 (2014)","key":"27_CR15","DOI":"10.1109\/ICPR.2014.504"},{"doi-asserted-by":"crossref","unstructured":"Gao, S., Wang, C., Xiao, B., Shi, C., Zhou, W., Zhang, Z.: Learning co-occurrence strokes for scene character recognition based on spatiality embedded dictionary. In: Proceedings ICIP, pp. 5956\u20135960 (2014)","key":"27_CR16","DOI":"10.1109\/ICIP.2014.7026202"},{"doi-asserted-by":"crossref","unstructured":"Tan, Z.R., Tian, S., Tan, C.L.: Using pyramid of histogram of oriented gradients on natural scene text recognition. In: Proceedings ICIP, pp. 2629\u20132633 (2014)","key":"27_CR17","DOI":"10.1109\/ICIP.2014.7025532"},{"doi-asserted-by":"crossref","unstructured":"Gao, S., Wang, C., Xiao, B., Shi, C., Zhang, Z.: Stroke bank: a high-level representation for scene character recognition. In: Proceedings ICPR, pp. 2909\u20132913 (2014)","key":"27_CR18","DOI":"10.1109\/ICPR.2014.501"},{"doi-asserted-by":"crossref","unstructured":"Lee, C.-Y., Bhardwaj, A., Di, W., Jagadeesh, V., Piramuthu, R.: Region-based discriminative feature pooling for scene text recognition. In: Proceedings CVPR, pp. 4050\u20134057 (2014)","key":"27_CR19","DOI":"10.1109\/CVPR.2014.516"},{"doi-asserted-by":"crossref","unstructured":"Tian, S., Lu, S., Su, B., Tan, C.L.: Scene text recognition using co-occurrence of histogram of oriented gradients. In: Proceedings ICDAR, pp. 912\u2013916 (2013)","key":"27_CR20","DOI":"10.1109\/ICDAR.2013.186"},{"doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: Image retrieval using textual cues. In: Proceedings ICCV, pp. 3040\u20133047 (2013)","key":"27_CR21","DOI":"10.1109\/ICCV.2013.378"},{"doi-asserted-by":"crossref","unstructured":"Yi, C., Yang, X., Tian, Y.: Feature representations for scene text character recognition: a comparative study. In: Proceedings ICDAR, pp. 907\u2013911 (2013)","key":"27_CR22","DOI":"10.1109\/ICDAR.2013.185"},{"key":"27_CR23","series-title":"LNCS","first-page":"770","volume-title":"ACCV 2010, Part III","author":"L Neumann","year":"2011","unstructured":"Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 770\u2013783. Springer, Heidelberg (2011)"},{"doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings CVPR, pp. 886\u2013893 (2005)","key":"27_CR24","DOI":"10.1109\/CVPR.2005.177"},{"doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: Top-down and bottom-up cues for scene text recognition. In: Proceedings CVPR, pp. 2687\u20132694 (2012)","key":"27_CR25","DOI":"10.1109\/CVPR.2012.6247990"},{"doi-asserted-by":"crossref","unstructured":"Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S., Zhang, Z.: Scene text recognition using part-based tree-structured character detection. In: Proceedings CVPR, pp. 2961\u20132968 (2013)","key":"27_CR26","DOI":"10.1109\/CVPR.2013.381"},{"issue":"9","key":"27_CR27","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.1016\/j.patcog.2014.03.023","volume":"47","author":"C Shi","year":"2014","unstructured":"Shi, C., Wang, C., Xiao, B., Gao, S., Hu, J.: End-to-end scene text recognition using tree-structured models. Pattern Recognit. 47(9), 2853\u20132866 (2014)","journal-title":"Pattern Recognit."},{"issue":"7","key":"27_CR28","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1109\/TCSVT.2014.2302522","volume":"24","author":"C Shi","year":"2014","unstructured":"Shi, C., Wang, C., Xiao, B., Gao, S., Hu, J.: Scene text recognition using structure-guided character detection and linguistic knowledge. IEEE Trans. Circuits Syst. Video Technol. 24(7), 1235\u20131250 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"doi-asserted-by":"crossref","unstructured":"Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: Proceedings CVPR, pp. 2879\u20132886 (2012)","key":"27_CR29","DOI":"10.1109\/CVPR.2012.6248014"},{"doi-asserted-by":"crossref","unstructured":"Zhang, D., Wang, D.-H., Wang, H.: Scene text recognition using sparse coding based features. In: Proceedings ICIP, pp. 1066\u20131070 (2014)","key":"27_CR30","DOI":"10.1109\/ICIP.2014.7025212"},{"doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Scene text localization and recognition with oriented stroke detection. In: Proceedings ICCV, pp. 97\u2013104 (2013)","key":"27_CR31","DOI":"10.1109\/ICCV.2013.19"},{"key":"27_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-319-16865-4_3","volume-title":"Computer Vision \u2013 ACCV 2014","author":"B Su","year":"2015","unstructured":"Su, B., Lu, S.: Accurate scene text recognition based on recurrent neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 35\u201348. Springer, Heidelberg (2015)"},{"doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: PhotoOCR: reading text in uncontrolled conditions. In: Proceedings ICCV, pp. 785\u2013792 (2013)","key":"27_CR33","DOI":"10.1109\/ICCV.2013.102"},{"issue":"3","key":"27_CR34","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/89.568732","volume":"5","author":"B-H Juang","year":"1997","unstructured":"Juang, B.-H., Chou, W., Lee, C.-H.: Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5(3), 257\u2013265 (1997)","journal-title":"IEEE Trans. Speech Audio Process."},{"doi-asserted-by":"crossref","unstructured":"Goel, V., Mishra, A., Alahari, K., Jawahar, C.V.: Whole is greater than sum of parts: recognizing scene text words. In: Proceedings ICDAR, pp. 398\u2013402 (2013)","key":"27_CR35","DOI":"10.1109\/ICDAR.2013.87"},{"doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings CVPR, pp. 3538\u20133545 (2012)","key":"27_CR36","DOI":"10.1109\/CVPR.2012.6248097"},{"unstructured":"Yildirim, G., Achanta, R., Susstrunk, S.: Text recognition in natural images using multiclass hough forests. In: Proceedings of International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (2013)","key":"27_CR37"},{"doi-asserted-by":"crossref","unstructured":"Feild, J.L., Learned-Miller, E.G.: Improving open-vocabulary scene text recognition. In: Proceedings ICDAR, pp. 604\u2013608 (2013)","key":"27_CR38","DOI":"10.1109\/ICDAR.2013.125"},{"key":"27_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-642-33783-3_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"T Novikova","year":"2012","unstructured":"Novikova, T., Barinova, O., Kohli, P., Lempitsky, V.: Large-lexicon attribute-consistent text recognition in natural images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 752\u2013765. Springer, Heidelberg (2012)"},{"issue":"2","key":"27_CR40","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1109\/TPAMI.2013.126","volume":"36","author":"JJ Weinman","year":"2014","unstructured":"Weinman, J.J., Butler, Z., Knoll, D., Feild, J.L.: Toward integrated scene text reading. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 375\u2013387 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21969-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T21:12:30Z","timestamp":1748553150000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-21969-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319219684","9783319219691"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21969-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}