{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:51:54Z","timestamp":1770277914579,"version":"3.49.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2017,5,5]],"date-time":"2017-05-05T00:00:00Z","timestamp":1493942400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1007\/s11042-017-4750-6","type":"journal-article","created":{"date-parts":[[2017,5,5]],"date-time":"2017-05-05T20:12:51Z","timestamp":1494015171000},"page":"8551-8578","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Text recognition in scene image and video frame using Color Channel selection"],"prefix":"10.1007","volume":"77","author":[{"given":"Ayan Kumar","family":"Bhunia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautam","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Partha Pratim","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Balasubramanian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,5]]},"reference":[{"key":"4750_CR1","unstructured":"ABBYY FineReader 9.0. \nhttp:\/\/www.abbyy.com\/"},{"key":"4750_CR2","unstructured":"Alsharif O, Pineau J (2013) End-to-end text recognition with hybrid HMM maxout models. arXiv preprint arXiv:1310.1811"},{"key":"4750_CR3","doi-asserted-by":"crossref","unstructured":"Bhunia AK, Das A, Roy PP, Pal U (2015) A comparative study of features of handwritten Bangla text recognition. In Proceedings of International Conference on Document Analysis and Recognition, pp. 636-640","DOI":"10.1109\/ICDAR.2015.7333839"},{"key":"4750_CR4","doi-asserted-by":"crossref","unstructured":"Bissacco A, Cummins M, Netzer Y, Neven H (2013) PhotoOCR: reading text in uncontrolled conditions. In Proceedings of International Conference on Computer Vision, pp. 785-792","DOI":"10.1109\/ICCV.2013.102"},{"key":"4750_CR5","doi-asserted-by":"crossref","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In Proceedings of ACM International Conference on Image and Video Retrieval, pp. 401-408","DOI":"10.1145\/1282280.1282340"},{"key":"4750_CR6","doi-asserted-by":"crossref","unstructured":"Chattopadhyay T, Reddy VR, Garain U (2013) Automatic selection of binarization method for robust OCR. In Proceedings of International Conference on Document Analysis and Recognition, pp. 1170-1174","DOI":"10.1109\/ICDAR.2013.237"},{"issue":"9","key":"4750_CR7","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1016\/j.patrec.2004.11.019","volume":"26","author":"D Chen","year":"2005","unstructured":"Chen D, Odobez JM (2005) Video text recognition using sequential Monte Carlo and error voting methods. Pattern Recogn Lett 26(9):1386\u20131403","journal-title":"Pattern Recogn Lett"},{"issue":"9","key":"4750_CR8","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1109\/TPAMI.2009.155","volume":"32","author":"J Chen","year":"2010","unstructured":"Chen J, Shan S, He C, Zhao G, Pietikainen M, Chen X, Gao W (2010) WLD: a robust local image descriptor. IEEE Trans Pattern Anal Mach Intell 32(9):1705\u20131720","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4750_CR9","doi-asserted-by":"crossref","unstructured":"Godbole S, Sarawagi S (2004) Discriminative methods for multi-labeled classification. In Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 22-30","DOI":"10.1007\/978-3-540-24775-3_5"},{"key":"4750_CR10","unstructured":"Gonzalez R. C., Woods R. E. (2006) Digital image processing(3rd Edition). Prentice-Hall, Upper Saddle River"},{"issue":"3","key":"4750_CR11","first-page":"228","volume":"16","author":"A Gonzalez","year":"2015","unstructured":"Gonzalez A, Bergasa LM, Yebes JJ (2015) Text detection and recognition on traffic panels from street-level imagery using visual appearance. IEEE Trans Intell Transp Syst 16(3):228\u2013238","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"4750_CR12","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1109\/TITS.2014.2363167","volume":"16","author":"J Greenhalgh","year":"2015","unstructured":"Greenhalgh J, Mirmehdi M (2015) Recognizing text-based traffic signs. IEEE Trans Intell Transp Syst 16(3):1360\u20131369","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"6","key":"4750_CR13","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"3","author":"RM Haralick","year":"1973","unstructured":"Haralick RM, Shanmugam K (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610\u2013621","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"4750_CR14","unstructured":"Huang R, Oba S, Shivakumara P, Uchida S (2012) Scene character detection and recognition based on multiple hypotheses framework. In Proceedings of International Conference on Pattern Recognition, pp. 717-720"},{"key":"4750_CR15","doi-asserted-by":"crossref","unstructured":"Huang W, Lin Z, Yang J, Wang J (2013) Text localization in natural images using stroke feature transform and text covariance descriptors. In Proceedings of International Conference on Computer Vision, pp. 1241-1248","DOI":"10.1109\/ICCV.2013.157"},{"key":"4750_CR16","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Deep features for text spotting. In Proceedings of European Conference on Computer Vision, pp. 512-528","DOI":"10.1007\/978-3-319-10593-2_34"},{"issue":"1","key":"4750_CR17","doi-asserted-by":"crossref","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 (2016) Reading text in the wild with convolutional neural networks. Int J Comput Vis 116(1):1\u201320","journal-title":"Int J Comput Vis"},{"key":"4750_CR18","doi-asserted-by":"crossref","unstructured":"Jain A, Peng X, Zhuang X, Natarajan P, Cao H (2014) Text detection and recognition in natural scenes and consumer videos. In Proceedings of International Conference on Acoustics, Speech and Signal Processing, pp. 1245\u20131249","DOI":"10.1109\/ICASSP.2014.6853796"},{"key":"4750_CR19","unstructured":"Jetley S, Behlhe S, Koppula VK, Nagi A (2012) Two-stage hybrid binarization around fringe map based text line segmentation for document images. In Proceedings of International Conference on Pattern Recognition, pp. 343-346"},{"key":"4750_CR20","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, Iwamura M, Gomez L, Robles S, Mas J, Fernandez D, Almazan J, de lasHeras, LP (2013) ICDAR 2013 robust reading competition. In Proceedings of International Conference on Document Analysis and Recognition, pp. 1484\u20131493","DOI":"10.1109\/ICDAR.2013.221"},{"key":"4750_CR21","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S, Bagdanow A, Iwamura M, Matas J, Neumann L, Chandrsekhar VR (2015) ICDAR 2015 competition on robust reading. In Proceedings of International Conference on Document Analysis and Recognition, pp. 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"4750_CR22","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.patcog.2016.01.008","volume":"54","author":"V Khare","year":"2016","unstructured":"Khare V, Shivakumara P, Raveendran P, Blumenstein M (2016) A blind deconvolution model for scene text detection and recognition in video. Pattern Recogn 54:128\u2013148","journal-title":"Pattern Recogn"},{"issue":"1","key":"4750_CR23","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1023\/A:1011126920638","volume":"43","author":"T Leung","year":"2001","unstructured":"Leung T, Malik J (2001) Representing and recognizing the visual appearance of materials using three-dimensional textons. Int J Comput Vis 43(1):29\u201344","journal-title":"Int J Comput Vis"},{"issue":"4","key":"4750_CR24","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1109\/TIP.2002.999679","volume":"11","author":"C Liu","year":"2002","unstructured":"Liu C, Wechsler H (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans Image Process 11(4):467\u2013476","journal-title":"IEEE Trans Image Process"},{"key":"4750_CR25","doi-asserted-by":"crossref","unstructured":"Liu L, Li W, Tang S, Gong W (2012) A novel separating strategy for face hallucination. In Proceedings of International Conference on Image Processing, pp. 1849-1852","DOI":"10.1109\/ICIP.2012.6467243"},{"key":"4750_CR26","doi-asserted-by":"crossref","unstructured":"Liu L, Wiliem A, Chen S, Lovell BC (2014) Automatic image attribute selection for zero-shot learning of object categories. In Proceedings of International Conference on Pattern Recognition, pp. 2619-2624","DOI":"10.1109\/ICPR.2014.452"},{"key":"4750_CR27","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2013.09.056","volume":"139","author":"M Liu","year":"2014","unstructured":"Liu M, Zhang D, Chen S (2014) Attribute relation learning for zero-shot classification. Neurocomputing 139:34\u201346","journal-title":"Neurocomputing"},{"key":"4750_CR28","doi-asserted-by":"crossref","unstructured":"Lucas SM, Panaretos A, Sosa L, Tang A, Wong S, Young R (2003) ICDAR 2003 robust reading competitions. In Proceedings of International Conference on Document Analysis and Recognition, pp. 682\u2013687","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"4750_CR29","doi-asserted-by":"crossref","unstructured":"Lucas S, Panaretos A, Sosa L, Tang A, Wong S, Young R (2003) ICDAR 2003 robust reading competitions. In Proceedings of International Conference on Document Analysis and Recognition, pp. 682\u2013687","DOI":"10.1109\/ICDAR.2003.1227749"},{"issue":"7","key":"4750_CR30","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/34.192463","volume":"11","author":"SG Mallat","year":"1989","unstructured":"Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674\u2013693","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4750_CR31","doi-asserted-by":"crossref","unstructured":"Mishra A, Alahari K, Jawahar CV (2012) Top-down and bottom-up cues for scene text recognition. In Proceedings of. Computer Vision and Pattern Recognition, pp. 2687\u20132694","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"4750_CR32","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.jvcir.2017.03.002","volume":"46","author":"A Mittal","year":"2017","unstructured":"Mittal A, Roy PP, Singh P, Balasubramanian R (2017) Rotation and script independent text detection from video frames using sub pixel mapping. J Vis Commun Image Represent 46:187\u2013198","journal-title":"J Vis Commun Image Represent"},{"key":"4750_CR33","unstructured":"Neuman L, Matas J (2010) A method for text localization and recognition in real world images. In Proceedings of Asian Conference on Computer Vision, pp. 770-783"},{"key":"4750_CR34","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2012) Real-time scene text localization and recognition. In Proceedings of Computer Vision and Pattern Recognition, pp. 3538-3545","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"4750_CR35","doi-asserted-by":"crossref","unstructured":"Nguyen P, Wang K, Belongie S (2014) Video text detection and recognition: dataset and benchmark. In Proceedings of Winter Conference on Applications of Computer Vision, pp. 776\u2013783","DOI":"10.1109\/WACV.2014.6836024"},{"key":"4750_CR36","doi-asserted-by":"crossref","unstructured":"Novikova MT, Barinova O, Kohli P, Lempitsky V (2012) Large-lexicon attribute-consistent text recognition in natural images. In Proceedings of European Conference on Computer Vision, pp. 752\u2013765","DOI":"10.1007\/978-3-642-33783-3_54"},{"issue":"7","key":"4750_CR37","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971\u2013987","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4750_CR38","doi-asserted-by":"crossref","unstructured":"Ojansivu V, Heikkila J (2008) Blur insensitive texture classification using local phase quantization. International conference on image and signal processing, pp. 236\u2013243","DOI":"10.1007\/978-3-540-69905-7_27"},{"key":"4750_CR39","doi-asserted-by":"crossref","first-page":"4124","DOI":"10.1016\/j.patcog.2010.06.017","volume":"43","author":"U Pal","year":"2010","unstructured":"Pal U, Roy PP, Tripathy N, Llad\u00f3s J (2010) Multi-oriented Bangla and Devanagari text recognition. Pattern Recogn 43:4124\u20134136","journal-title":"Pattern Recogn"},{"key":"4750_CR40","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Tian S, Tan CL (2013) Recognizing text with perspective distortion in natural scenes. In Proceedings of International Conference on Computer Vision, pp. 569-576","DOI":"10.1109\/ICCV.2013.76"},{"key":"4750_CR41","unstructured":"Roy S, Shivakumara P, Roy PP, Tan CL (2012) Wavelet-gradient-fusion for video text binarization. In Proceedings of International Conference on Pattern Recognition, pp. 3300-3303"},{"key":"4750_CR42","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1016\/j.patcog.2011.09.026","volume":"45","author":"PP Roy","year":"2012","unstructured":"Roy PP, Pal U, Llad\u00f3s J, Delalandre M (2012) Multi-oriented touching text character segmentation in graphical documents using dynamic programming. Pattern Recogn 45:1972\u20131983","journal-title":"Pattern Recogn"},{"issue":"5","key":"4750_CR43","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1016\/j.patcog.2011.09.026","volume":"45","author":"PP Roy","year":"2012","unstructured":"Roy PP, Pal U, Llad\u00f3s J, Delalandre M (2012) Multi-oriented touching text character segmentation in graphical documents using dynamic programming. Pattern Recognit 45(5):1972\u20131983","journal-title":"Pattern Recognit"},{"key":"4750_CR44","doi-asserted-by":"crossref","unstructured":"Roy S, Roy PP, Shivakumara P, Louloudis G, Tan CL, Pal U (2013) HMM-based multi oriented text recognition in natural scene image. In Proceedings of Asian Conference on Pattern Recognition, pp. 288\u2013292","DOI":"10.1109\/ACPR.2013.60"},{"issue":"13","key":"4750_CR45","doi-asserted-by":"crossref","first-page":"5554","DOI":"10.1016\/j.eswa.2015.02.030","volume":"42","author":"S Roy","year":"2015","unstructured":"Roy S, Shivakumara P, Roy PP, Pal U, Tan CL, Lu T (2015) Bayesian classifier for multi-oriented video text recognition system. Expert Systems with Applications 42(13):5554\u20135566","journal-title":"Expert Systems with Applications"},{"key":"4750_CR46","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.patcog.2015.10.011","volume":"52","author":"S Roy","year":"2016","unstructured":"Roy S, Shivakumara P, Jalab HA, Ibrahim RW, Pal U, Lu T (2016) Fractional Poisson enhancement model for text detection and recognition in video frames. Pattern Recogn 52:433\u2013447","journal-title":"Pattern Recogn"},{"key":"4750_CR47","doi-asserted-by":"crossref","unstructured":"Saidane Z, Garcia C (2007) Robust binarization for video text recognition. In Proceedings of International Conference on Document Analysis and Recognition, pp. 874-879","DOI":"10.1109\/ICDAR.2007.4377040"},{"key":"4750_CR48","unstructured":"Saidane Z, Gracia C (2007) Automatic scene text recognition using a convolutional neural network. In Proceedings of Camera-Based Document Analysis and Recognition, pp. 100-107"},{"key":"4750_CR49","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.patcog.2016.08.021","volume":"61","author":"P Shivakumara","year":"2017","unstructured":"Shivakumara P, Raghavendra R, Qin L, Raja KB, Lu T, Pal U (2017) A new multi-modal approach to bib number\/text detection and recognition in Marathon images. Pattern Recogn 61:479\u2013491","journal-title":"Pattern Recogn"},{"key":"4750_CR50","unstructured":"Tesseract. \nhttp:\/\/code.google.com\/p\/tesseract-ocr\/"},{"key":"4750_CR51","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s11263-005-6642-x","volume":"61","author":"Z Tu","year":"2005","unstructured":"Tu Z, Chen X, Yuille AL, Zhu SC (2005) Image parsing: unifying segmentation, detection and recognition. Int J Comput Vis 61:113\u2013140","journal-title":"Int J Comput Vis"},{"key":"4750_CR52","doi-asserted-by":"crossref","unstructured":"Wang K, Belongie S (2010) Word spotting in the wild. In Proceedings of European Conference on Computer Vision, pp. 591\u2013604","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"4750_CR53","unstructured":"Wang K, Babenko B, Belongie S (2011) End to end scene text recognition. In Proceedings of International Conference on Computer Vision, pp. 1457-1464"},{"issue":"12","key":"4750_CR54","doi-asserted-by":"crossref","first-page":"5622","DOI":"10.1109\/TIP.2016.2607426","volume":"25","author":"Y Wu","year":"2016","unstructured":"Wu Y, Shivakumara P, Lu T, Tan CL, Blumenstein M, Kumar GH (2016) Contour restoration of text components for recognition in video\/scene images. IEEE Trans Image Process 25(12):5622\u20135634","journal-title":"IEEE Trans Image Process"},{"key":"4750_CR55","unstructured":"Xin L, Guo Y (2013) Active learning with multi-label SVM classification. In Proceedings of International Joint Conference on Artificial Intelligence"},{"issue":"1","key":"4750_CR56","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s11042-012-1250-6","volume":"69","author":"H Yang","year":"2014","unstructured":"Yang H, Quehl B, Sack H (2014) A framework for improved video text detection and recognition. Multimedia Tools and Applications 69(1):217\u2013245","journal-title":"Multimedia Tools and Applications"},{"key":"4750_CR57","unstructured":"Yao C, Bai X, Liu W, Ma Y, Tu Z (2012) Detecting texts of arbitrary orientations in natural images. In Proceedings of Computer Vision and Pattern Recognition, pp. 1083-1090"},{"key":"4750_CR58","doi-asserted-by":"crossref","unstructured":"Yao C, Bai X, Shi B, Liu W (2014) Strokelets: a learned multi-scale representation for scene text recognition. In Proceedings of Computer Vision and Pattern Recognition, pp. 4042-4049","DOI":"10.1109\/CVPR.2014.515"},{"issue":"7","key":"4750_CR59","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye Q, Doermann DS (2015) Text detection and recognition in imagery: a survey. IEEE Trans Pattern Anal Mach Intell 37(7):1480\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"4750_CR60","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TIP.2012.2214045","volume":"22","author":"J Zhang","year":"2013","unstructured":"Zhang J, Liang J, Zhao H (2013) Local energy pattern for texture classification using self-adaptive quantization thresholds. IEEE Trans Image Process 22(1):31\u201342","journal-title":"IEEE Trans Image Process"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4750-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4750-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4750-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,4,5]],"date-time":"2018-04-05T10:18:45Z","timestamp":1522923525000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4750-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,5]]},"references-count":60,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["4750"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4750-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,5]]}}}