{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T03:03:50Z","timestamp":1761102230496},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,1,6]],"date-time":"2017-01-06T00:00:00Z","timestamp":1483660800000},"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":[[2018,1]]},"DOI":"10.1007\/s11042-016-4292-3","type":"journal-article","created":{"date-parts":[[2017,1,6]],"date-time":"2017-01-06T08:17:47Z","timestamp":1483690667000},"page":"985-1008","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Frame selection for OCR from video stream of book flipping"],"prefix":"10.1007","volume":"77","author":[{"given":"Dibyayan","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Partha Pratim","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajkumar","family":"Saini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose M.","family":"Alvarez","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":[[2017,1,6]]},"reference":[{"key":"4292_CR1","doi-asserted-by":"crossref","unstructured":"Breuel TM (2008) The OCRopus open source OCR system. In: Proceedings of DRR","DOI":"10.1117\/12.783598"},{"key":"4292_CR2","doi-asserted-by":"crossref","unstructured":"Bosamiya JH, Agrawal P, Roy PP, Balasubramanian R (2015) Script independent scene text segmentation using fast stroke width transform and GrabCut. In: 3rd IAPR Asian conference on pattern recognition (ACPR), pp 151\u2013155","DOI":"10.1109\/ACPR.2015.7486484"},{"issue":"6","key":"4292_CR3","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679\u2013698","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4292_CR4","doi-asserted-by":"crossref","unstructured":"Chakraborty D, Roy PP, Pal U, Alvarez JM (2013) OCR from video stream of book flipping. In: Proceedings of the 2nd Asian conference on pattern recognition, pp 130\u2013134","DOI":"10.1109\/ACPR.2013.24"},{"key":"4292_CR5","doi-asserted-by":"crossref","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","DOI":"10.1145\/1961189.1961199"},{"key":"4292_CR6","unstructured":"Cunzhao S, Wang C, Xiao B, Zhang Y, Gao S, Zhang Z (2013) Scene text recognition using part-based tree-structured character detection. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 2961\u20132968"},{"key":"4292_CR7","doi-asserted-by":"crossref","unstructured":"Das D, Datong C, Hauptmann AG (2008) Improving multimedia retrieval with a video OCR, pp 68200B-68200B","DOI":"10.1117\/12.766931"},{"key":"4292_CR8","unstructured":"Fujinami K, Inagawa N (2009) Page-flipping detection and information presentation for implicit interaction with a book. Int J Multimedia Ubiquit Eng 93\u2013112"},{"key":"4292_CR9","unstructured":"Hearn D, Baker MP (1994) Computer graphics. Addison-Wesley"},{"key":"4292_CR10","doi-asserted-by":"crossref","unstructured":"Iwamura M, Tsuji T, Horimatsu A, Kise K (2009) Real-time camera-based recognition of characters and pictograms. In: International conference on document analysis and recognition, pp 76\u201380","DOI":"10.1109\/ICDAR.2009.259"},{"key":"4292_CR11","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.1016\/S0167-8655(03)00105-3","volume":"24","author":"CW Lee","year":"2003","unstructured":"Lee CW, Jung K, Kim HJ (2003) Automatic text detection and removal in video sequences. Pattern Recogn Lett 24:2607\u20132623","journal-title":"Pattern Recogn Lett"},{"issue":"4","key":"4292_CR12","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/76.999203","volume":"12","author":"R Lienhart","year":"2002","unstructured":"Lienhart R, Wernicke A (2002) Localizing and segmenting text in images and videos. IEEE Trans Circuits Syst Video Technol 12(4):256\u2013268","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4292_CR13","doi-asserted-by":"crossref","unstructured":"Micusik B, Wildenauer H, Kosecka J (2008) Detection and matching of rectilinear structures. In: Proceedings of computer vision and pattern recognition (CVPR), pp 1\u20137","DOI":"10.1109\/CVPR.2008.4587488"},{"key":"4292_CR14","doi-asserted-by":"crossref","unstructured":"Mishra A, Karteek A, Jawahar CV (2012) Top-down and bottom-up cues for scene text recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 2687\u20132694","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"4292_CR15","unstructured":"Nakashima T, Watanabe Y, Komuro T, Ishikawa M (2009) Book flipping scanning. In: Symposium on user interface software and technology, vol 22, pp 79\u201380"},{"key":"4292_CR16","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2012) Real-time scene text localization and recognition, pp 3538\u20133545","DOI":"10.1109\/CVPR.2012.6248097"},{"issue":"3","key":"4292_CR17","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s00530-004-0157-0","volume":"10","author":"CW Ngo","year":"2005","unstructured":"Ngo CW, Chan CK (2005) Video text detection and segmentation for optical character recognition. Multimedia Systems 10(3):261\u2013272","journal-title":"Multimedia Systems"},{"key":"4292_CR18","unstructured":"Niblack W (1986) An introduction to digital image processing. Prentice Hall, pp 115\u2013116"},{"key":"4292_CR19","doi-asserted-by":"crossref","unstructured":"Ojala T, Pietik\u00e4inen M, M\u00e4enp\u00e4\u00e4 T (2001) A generalized Local Binary Pattern operator for multiresolution gray scale and rotation invariant texture classification. In: Proceedings of international conference on advances in pattern recognition, pp 399\u2013408","DOI":"10.1007\/3-540-44732-6_41"},{"issue":"7","key":"4292_CR20","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietik\u00e4inen M, M\u00e4enp\u00e4\u00e4 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"},{"issue":"3","key":"4292_CR21","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of spatial envelope. Int J Comput Vis 42(3):145\u2013175","journal-title":"Int J Comput Vis"},{"key":"4292_CR22","unstructured":"onlineocr.net - Free Online OCR service, convert scanned PDF and images to Word, Text"},{"issue":"1","key":"4292_CR23","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62\u201366","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"4292_CR24","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: 2nd IAPR Asian conference on pattern recognition, pp 288\u2013292","DOI":"10.1109\/ACPR.2013.60"},{"key":"4292_CR25","doi-asserted-by":"crossref","unstructured":"Sato T, Kanade T, Hughes EK, Smith MA (1998) Video OCR for digital news archive, In Proc. In: IEEE international workshop on content-based access of image and video database, pp 52\u201360","DOI":"10.1109\/CAIVD.1998.646033"},{"issue":"2","key":"4292_CR26","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","volume":"33","author":"J Sauvola","year":"2000","unstructured":"Sauvola J, Pietik\u00e4inen M (2000) Adaptive document image binarization. Pattern Recogn 33(2):225\u2013236","journal-title":"Pattern Recogn"},{"key":"4292_CR27","unstructured":"Shibayama H, Watanabe Y, Ishikawa M (2012) Reconstruction of 3D surface and restoration of flat document image from monocular image sequence. In: Asian conference on computer vision, pp 350\u2013364"},{"key":"4292_CR28","doi-asserted-by":"crossref","unstructured":"Shivakumara P, Bhowmick S, Su B, Tan CL, Pal U (2011) A new gradient based character segmentation method for video text recognition. In: International conference on document analysis and recognition, pp 126\u2013130","DOI":"10.1109\/ICDAR.2011.34"},{"key":"4292_CR29","doi-asserted-by":"crossref","unstructured":"Singh M, Kaur A (2015) An efficient hybrid scheme for key frame extraction and text localization in video. In: International conference on advances in computing, communications and informatics, pp 1250\u20131254","DOI":"10.1109\/ICACCI.2015.7275784"},{"key":"4292_CR30","doi-asserted-by":"crossref","unstructured":"Smith R (2007) An overview of the Tesseract OCR engine. In: Proceedings of 9th international conference on document analysis and recognition, pp 629\u2013633","DOI":"10.1109\/ICDAR.2007.4376991"},{"issue":"4","key":"4292_CR31","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/TIP.2012.2231089","volume":"22","author":"B Su","year":"2013","unstructured":"Su B, Lu S, Tan CL (2013) Robust document image binarization technique for degraded document images. IEEE Trans Image Processing 22(4):1408\u20131417","journal-title":"IEEE Trans Image Processing"},{"key":"4292_CR32","doi-asserted-by":"crossref","unstructured":"Vajda S, Rothacker L, Fink GA (2011) A method for camera-based interactive whiteboard reading","DOI":"10.1007\/978-3-642-29364-1_9"},{"key":"4292_CR33","doi-asserted-by":"crossref","unstructured":"Vapnik V (1995) The nature of statistical learning theory. Springer Verlang","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"4292_CR34","doi-asserted-by":"crossref","unstructured":"Wu V, Manmatha R, Riseman EM (1997) Finding text in images. In: Proceedings of ACM international conference on digital libraries, pp 23\u201326","DOI":"10.1145\/263690.263766"},{"key":"4292_CR35","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: IEEE conference on computer vision and pattern recognition, pp 4042\u20134049","DOI":"10.1109\/CVPR.2014.515"},{"issue":"9","key":"4292_CR36","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1109\/TIP.2011.2126586","volume":"20","author":"C Yi","year":"2011","unstructured":"Yi C, Tian Y (2011) Text string detection from natural scenes by structure-based partition and grouping. IEEE Trans Image Process 20(9):2594\u20132605","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"4292_CR37","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","volume":"36","author":"XC Yin","year":"2014","unstructured":"Yin XC, Yin X, Huang K, Hao HW (2014) Robust text detection in natural scene images. IEEE Trans Pattern Anal Mach Intell 36(5):970\u2013983","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"4292_CR38","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"XC Yin","year":"2015","unstructured":"Yin XC, Pei WY, Zhang J, Hao HW (2015) Multi-orientation scene text detection with adaptive clustering. IEEE Trans Pattern Anal Mach Intell 37 (9):1930\u20131937","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4292_CR39","unstructured":"Zang J, Kasturi R (2008) Extraction of text objects in video documents: recent progress. In: Proceedings of 8th international association pattern recognition international workshop document analysis systems, pp 5\u201317"},{"key":"4292_CR40","doi-asserted-by":"crossref","unstructured":"Zhong Y, Karu K, Jain AK (1995) Locating text in complex color images. In: Proceedings of 3rd international conference document analysis and recognition, p 146","DOI":"10.1109\/ICDAR.1995.598963"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-016-4292-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-4292-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-4292-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T06:38:07Z","timestamp":1568702287000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-016-4292-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,6]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["4292"],"URL":"https:\/\/doi.org\/10.1007\/s11042-016-4292-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,6]]}}}