{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:48:41Z","timestamp":1764841721032,"version":"3.40.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,2,19]],"date-time":"2013-02-19T00:00:00Z","timestamp":1361232000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1007\/s10032-013-0202-7","type":"journal-article","created":{"date-parts":[[2013,2,19]],"date-time":"2013-02-19T05:57:43Z","timestamp":1361253463000},"page":"19-31","source":"Crossref","is-referenced-by-count":13,"title":["Text recognition in multimedia documents: a study of two neural-based OCRs using and avoiding character segmentation"],"prefix":"10.1007","volume":"17","author":[{"given":"Khaoula","family":"Elagouni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Garcia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franck","family":"Mamalet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascale","family":"S\u00e9billot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,2,19]]},"reference":[{"issue":"7","key":"202_CR1","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1109\/29.32278","volume":"37","author":"L Bahl","year":"2002","unstructured":"Bahl, L., Brown, P., de Souza, P., Mercer, R.: A tree-based statistical language model for natural language speech recognition. IEEE Trans. Acous. Speech Sig. Process. 37(7), 1001\u20131008 (2002)","journal-title":"IEEE Trans. Acous. Speech Sig. Process."},{"issue":"7","key":"202_CR2","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1109\/34.506792","volume":"18","author":"R Casey","year":"2002","unstructured":"Casey, R., Lecolinet, E.: A survey of methods and strategies in character segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(7), 690\u2013706 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"202_CR3","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/j.patcog.2003.06.001","volume":"37","author":"D Chen","year":"2004","unstructured":"Chen, D., Odobez, J., Bourlard, H.: Text detection and recognition in images and video frames. Pattern Recogn. 37(3), 595\u2013608 (2004)","journal-title":"Pattern Recogn."},{"key":"202_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., Ghosh, D., Ranganath, S.: Video-text extraction and recognition. In: IEEE Region 10 Conference, TENCON\u201904, vol. 1, pp. 319\u2013322 (2005)","DOI":"10.1109\/TENCON.2004.1414421"},{"key":"202_CR5","doi-asserted-by":"crossref","unstructured":"Coates, A., Carpenter, B., Case, C., Satheesh, S., Suresh, B., Wang, T., Wu, D., Ng, A.: Text detection and character recognition in scene images with unsupervised feature learning. In: International Conference on Document Analysis and Recognition, pp. 440\u2013445 (2011)","DOI":"10.1109\/ICDAR.2011.95"},{"key":"202_CR6","unstructured":"Delakis, M., Garcia, C.: Text detection with convolutional neural networks. In: International Conference on Computer Vision Theory and Applications, vol. 2, pp. 290\u2013294 (2008)"},{"issue":"1","key":"202_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodological) 39(1), 1\u201338 (1977)","journal-title":"J. R. Stat. Soc. Ser. B (Methodological)"},{"key":"202_CR8","doi-asserted-by":"crossref","unstructured":"Dorai, C., Aradhye, H., Shim, J.C.: End-to-end video text recognition for multimedia content analysis. In: International Conference on Multimedia and Expo, pp. 601\u2013604 (2001)","DOI":"10.1109\/ICME.2001.1237761"},{"key":"202_CR9","doi-asserted-by":"crossref","unstructured":"El Abed, H., Margner, V.: Comparison of different preprocessing and feature extraction methods for offline recognition of handwritten Arabic words. In: International Conference on Document Analysis and Recognition, vol. 2, pp. 974\u2013978 (2007)","DOI":"10.1109\/ICDAR.2007.4377060"},{"key":"202_CR10","doi-asserted-by":"crossref","unstructured":"Elagouni, K., Garcia, C., Mamalet, F., S\u00e9billot, P.: Combining multi-scale character recognition and linguistic knowledge for natural scene text OCR. In: International Workshop on Document Analysis Systems, pp. 120\u2013124 (2012)","DOI":"10.1109\/DAS.2012.26"},{"key":"202_CR11","doi-asserted-by":"crossref","unstructured":"Elagouni, K., Garcia, C., S\u00e9billot, P.: A comprehensive neural-based approach for text recognition in videos using natural language processing. In: International Conference on Multimedia Retrieval (2011)","DOI":"10.1145\/1991996.1992019"},{"issue":"11","key":"202_CR12","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TPAMI.2004.97","volume":"26","author":"C Garcia","year":"2004","unstructured":"Garcia, C., Delakis, M.: Convolutional face finder: a neural architecture for fast and robust face detection. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1408\u20131423 (2004)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"202_CR13","unstructured":"Halima, M., Karray, H., Alimi, A.: A comprehensive method for Arabic video text detection, localization, extraction and recognition. Adv. Multimed. Inf. Process. 6298, 648\u2013659 (2011)"},{"key":"202_CR14","doi-asserted-by":"crossref","unstructured":"Hamdani, M., El Abed, H., Kherallah, M., Alimi, A.: Combining multiple HMMs using on-line and off-line features for off-line Arabic handwriting recognition. In: International Conference on Document Analysis and Recognition, pp. 201\u2013205 (2009)","DOI":"10.1109\/ICDAR.2009.40"},{"key":"202_CR15","doi-asserted-by":"crossref","unstructured":"Hua, X., Yin, P., Zhang, H.: Efficient video text recognition using multiple frame integration. In: International Conference on Image Processing, vol. 2, pp. 397\u2013400 (2002)","DOI":"10.1109\/ICIP.2002.1039971"},{"issue":"5","key":"202_CR16","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/j.patcog.2003.10.012","volume":"37","author":"K Jung","year":"2004","unstructured":"Jung, K., In Kim, K., Jain, A.K.: Text information extraction in images and video: a survey. Pattern Recogn. 37(5), 977\u2013997 (2004)","journal-title":"Pattern Recogn."},{"key":"202_CR17","unstructured":"Kopf, S., Haenselmann, T., Effelsberg, W.: Robust character recognition in low-resolution images and videos. Universit\u00e4t Mannheim\/Institut f\u00fcr Informatik (2005)"},{"key":"202_CR18","doi-asserted-by":"crossref","unstructured":"Kusachi, Y., Suzuki, A., Ito, N., Arakawa, K.: Kanji recognition in scene images without detection of text fields-robust against variation of viewpoint, contrast, and background texture. In: International Conference on Pattern Recognition, vol. 1, pp. 457\u2013460 (2004)","DOI":"10.1109\/ICPR.2004.1334163"},{"key":"202_CR19","unstructured":"LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. The handbook of brain theory and, neural networks, pp. 255\u2013258 (1995)"},{"issue":"11","key":"202_CR20","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"issue":"1","key":"202_CR21","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/83.817607","volume":"9","author":"H Li","year":"2000","unstructured":"Li, H., Doermann, D., Kia, O.: Automatic text detection and tracking in digital video. IEEE Trans. Image Process. 9(1), 147\u2013156 (2000)","journal-title":"IEEE Trans. Image Process."},{"issue":"14","key":"202_CR22","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1016\/j.patrec.2010.05.031","volume":"31","author":"M Li","year":"2010","unstructured":"Li, M., Bai, M., Wang, C., Xiao, B.: Conditional random field for text segmentation from images with complex background. Pattern Recogn. Lett. 31(14), 2295\u20132308 (2010)","journal-title":"Pattern Recogn. Lett."},{"key":"202_CR23","doi-asserted-by":"crossref","unstructured":"Lienhart, R., Stuber, F.: Automatic text recognition in digital videos. In: Proceedings of the SPIE Image and Video Processing IV, vol. 2666, pp. 180\u2013188 (1996)","DOI":"10.1117\/12.234741"},{"issue":"5","key":"202_CR24","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1016\/j.imavis.2006.05.011","volume":"25","author":"J Lim","year":"2007","unstructured":"Lim, J., Park, J., Medioni, G.: Text segmentation in color images using tensor voting. Image Vis. Comput. 25(5), 671\u2013685 (2007)","journal-title":"Image Vis. Comput."},{"key":"202_CR25","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1109\/ICDAR.2003.1227749","volume":"2","author":"S Lucas","year":"2003","unstructured":"Lucas, S., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. Int. J. Doc. Anal. Recogn. 2, 682\u2013687 (2003)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"202_CR26","doi-asserted-by":"crossref","unstructured":"Mancas-Thillou, C., Gosselin, B.: Character segmentation-by-recognition using log-Gabor filters. In: International Conference on Pattern Recognition, vol. 2, pp. 901\u2013904 (2006)","DOI":"10.1109\/ICPR.2006.362"},{"key":"202_CR27","doi-asserted-by":"crossref","unstructured":"Miao, G., Zhu, G., Jiang, S., Huang, Q., Changsheng, X., Gao, W.: A real-time score detection and recognition approach for broadcast basketball video. In: International Conference on Multimedia and Expo, pp. 1691\u20131694 (2007)","DOI":"10.1109\/ICME.2007.4284563"},{"key":"202_CR28","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: An MRF model for binarization of natural scene text. In: International Conference on Document Analysis and Recognition, pp. 11\u201316 (2011)","DOI":"10.1109\/ICDAR.2011.12"},{"key":"202_CR29","doi-asserted-by":"crossref","unstructured":"Negishi, K., Iwamura, M., Omachi, S., Aso, H.: Isolated character recognition by searching features in scene images. In: International Workshop on Camera-Based Document Analysis and Recognition, pp. 140\u2013147 (2005)","DOI":"10.1109\/ICDAR.2005.147"},{"key":"202_CR30","doi-asserted-by":"crossref","unstructured":"Ntirogiannis, K., Gatos, B., Pratikakis, I.: Binarization of textual content in video frames. In: International Conference on Document Analysis and Recognition, pp. 673\u2013677 (2011)","DOI":"10.1109\/ICDAR.2011.141"},{"key":"202_CR31","doi-asserted-by":"crossref","unstructured":"Phan, T., Shivakumara, P., Su, B., Tan, C.: A gradient vector flow-based method for video character segmentation. In: International Conference on Document Analysis and Recognition, pp. 1024\u20131028 (2011)","DOI":"10.1109\/ICDAR.2011.207"},{"key":"202_CR32","unstructured":"Sa\u00efdane, Z., Garcia, C.: Automatic scene text recognition using a convolutional neural network. In: Conference on Computer Vision and, Pattern Recognition, pp. 100\u2013106 (2007)"},{"key":"202_CR33","doi-asserted-by":"crossref","unstructured":"Sa\u00efdane, Z., Garcia, C.: Robust binarization for video text recognition. In: International Conference on Document Analysis and Recognition, vol. 2, pp. 874\u2013879 (2007)","DOI":"10.1109\/ICDAR.2007.4377040"},{"key":"202_CR34","doi-asserted-by":"crossref","unstructured":"Sa\u00efdane, Z., Garcia, C., Dugelay, J.: The image text recognition graph (iTRG). In: International Conference on Multimedia and Expo, pp. 266\u2013269 (2009)","DOI":"10.1109\/ICME.2009.5202486"},{"issue":"5","key":"202_CR35","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s005300050140","volume":"7","author":"T Sato","year":"1999","unstructured":"Sato, T., Kanade, T., Hughes, E., Smith, M., Satoh, S.: Video OCR: indexing digital news libraries by recognition of superimposed captions. Multimed. Syst. 7(5), 385\u2013395 (1999)","journal-title":"Multimed. Syst."},{"key":"202_CR36","doi-asserted-by":"crossref","unstructured":"Sharma, N., Pal, U., Blumenstein, M.: Recent advances in video based document processing: a review. In: International Workshop on Document Analysis Systems, pp. 63\u201368 (2012)","DOI":"10.1109\/DAS.2012.72"},{"key":"202_CR37","doi-asserted-by":"crossref","unstructured":"Shivakumara, P., Bhowmick, S., Su, B., Tan, C., Pal, U.: A new gradient based character segmentation method for video text recognition. In: International Conference on Document Analysis and Recognition, pp. 126\u2013130 (2011)","DOI":"10.1109\/ICDAR.2011.34"},{"key":"202_CR38","doi-asserted-by":"crossref","unstructured":"Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, vol. 2, pp. 958\u2013963 (2003)","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"202_CR39","doi-asserted-by":"crossref","unstructured":"Som, T., Can, D., Saraclar, M.: HMM-based sliding video text recognition for Turkish broadcast news. In: International Symposium on Computer and, Information Sciences, pp. 475\u2013479 (2009)","DOI":"10.1109\/ISCIS.2009.5291877"},{"key":"202_CR40","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM-An extensible language modeling toolkit. In: International Conference on Spoken Language Processing, vol. 3, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"202_CR41","doi-asserted-by":"crossref","unstructured":"Wakahara, T., Kita, K.: Binarization of color character strings in scene images using K-means clustering and support vector machines. In: International Conference on Document Analysis and Recognition, pp. 274\u2013278 (2011)","DOI":"10.1109\/ICDAR.2011.63"},{"key":"202_CR42","doi-asserted-by":"crossref","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: European Conference on Computer Vision, pp. 591\u2013604 (2010)","DOI":"10.1007\/978-3-642-15549-9_43"},{"issue":"10","key":"202_CR43","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1109\/TPAMI.2009.38","volume":"31","author":"J Weinman","year":"2009","unstructured":"Weinman, J., Learned-Miller, E., Hanson, A.: Scene text recognition using similarity and a lexicon with sparse belief propagation. Pattern Anal. Mach. Intell. 31(10), 1733\u20131746 (2009)","journal-title":"Pattern Anal. Mach. Intell."},{"issue":"1","key":"202_CR44","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/0165-0114(91)90046-S","volume":"40","author":"R Yager","year":"1991","unstructured":"Yager, R.: Connectives and quantifiers in fuzzy sets. Fuzzy Sets Syst. 40(1), 39\u201375 (1991)","journal-title":"Fuzzy Sets Syst."},{"key":"202_CR45","doi-asserted-by":"crossref","unstructured":"Yamazoe, T., Etoh, M., Yoshimura, T., Tsujino, K.: Hypothesis preservation approach to scene text recognition with weighted finite-state transducer. In: International Conference on Document Analysis and Recognition, pp. 359\u2013363 (2011)","DOI":"10.1109\/ICDAR.2011.80"},{"issue":"6","key":"202_CR46","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1016\/j.imavis.2005.01.004","volume":"23","author":"Q Ye","year":"2005","unstructured":"Ye, Q., Huang, Q., Gao, W., Zhao, D.: Fast and robust text detection in images and video frames. Image Vis. Comput. 23(6), 565\u2013576 (2005)","journal-title":"Image Vis. Comput."},{"key":"202_CR47","doi-asserted-by":"crossref","unstructured":"Yi, J., Peng, Y., Xiao, J.: Using multiple frame integration for the text recognition of video. In: International Conference on Document Analysis and Recognition, pp. 71\u201375 (2009)","DOI":"10.1109\/ICDAR.2009.58"},{"key":"202_CR48","doi-asserted-by":"crossref","unstructured":"Yokobayashi, M., Wakahara, T.: Segmentation and recognition of characters in scene images using selective binarization in color space and GAT correlation. In: International Conference on Document Analysis and Recognition, pp. 167\u2013171 (2005)","DOI":"10.1109\/ICDAR.2005.208"},{"key":"202_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, D., Chang, S.: A Bayesian framework for fusing multiple word knowledge models in videotext recognition. In: Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 528\u2013533 (2003)","DOI":"10.1109\/CVPR.2003.1211512"},{"key":"202_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Li, L., Tan, C.: Edge based binarization for video text images. In: International Conference on Pattern Recognition, pp. 133\u2013136 (2010)","DOI":"10.1109\/ICPR.2010.41"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-013-0202-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-013-0202-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-013-0202-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T21:36:30Z","timestamp":1745962590000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-013-0202-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,19]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["202"],"URL":"https:\/\/doi.org\/10.1007\/s10032-013-0202-7","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2013,2,19]]}}}