{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T10:33:53Z","timestamp":1791196433305,"version":"4.1.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,10,11]],"date-time":"2012-10-11T00:00:00Z","timestamp":1349913600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1007\/s11042-012-1250-6","type":"journal-article","created":{"date-parts":[[2012,10,11]],"date-time":"2012-10-11T10:39:04Z","timestamp":1349951944000},"page":"217-245","source":"Crossref","is-referenced-by-count":29,"title":["A framework for improved video text detection and recognition"],"prefix":"10.1007","volume":"69","author":[{"given":"Haojin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Quehl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harald","family":"Sack","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2012,10,11]]},"reference":[{"key":"1250_CR1","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1016\/j.imavis.2010.03.004","volume":"28","author":"M Anthimopoulos","year":"2010","unstructured":"Anthimopoulos M, Gatos B, Pratikakis I (2010) A two-stage scheme for text detection in video images. J Image Vis Comput 28:1413\u20131426","journal-title":"J Image Vis Comput"},{"key":"1250_CR2","doi-asserted-by":"crossref","unstructured":"Bhaskar H, Mihaylova L (2010) Combined feature-level video indexing using block-based motion estimation. In: Proc. of 13th conference on information fusion (FUSION). Edinburgh, pp\u00a01\u20138","DOI":"10.1109\/ICIF.2010.5712099"},{"issue":"6","key":"1250_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":"1250_CR4","doi-asserted-by":"crossref","unstructured":"Chen D, Odobez JM, Bourlard H (2004) Text detection and recognition in images and video frames. J Pattern Recogn Soc 37(3):595\u2013608","DOI":"10.1016\/j.patcog.2003.06.001"},{"key":"1250_CR5","doi-asserted-by":"crossref","unstructured":"Deza MM, Deza E (2009) Encyclopedia of distances. Springer","DOI":"10.1007\/978-3-642-00234-2"},{"key":"1250_CR6","doi-asserted-by":"crossref","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. In: Proc. of international conference on computer vision and pattern recognition, pp 2963\u20132970","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"1250_CR7","doi-asserted-by":"crossref","unstructured":"Gllavata J, Ewerth R, Freisleben B (2004) Text detection in images based on unsupervised classification of high-frequency wavelet coefficients. In: Proceedings of 17th international conference on (ICPR\u201904), vol\u00a01, pp\u00a0425\u2013428","DOI":"10.1109\/ICPR.2004.1334146"},{"key":"1250_CR8","doi-asserted-by":"crossref","unstructured":"Gllavata J, Qeli E, Freisleben B (2006) Detecting text in videos using fuzzy clustering ensembles. In: Proceedings of the 8th IEEE international symposium on multimedia, ISM \u201906. IEEE Computer Society. Washington, DC, pp\u00a0283\u2013290","DOI":"10.1109\/ISM.2006.60"},{"key":"1250_CR9","unstructured":"Hanif SM, Prevost L (2009) Text detection and localization in complex scene images using constrained adaboost algorithm. In: Proceedings of the 2009 10th international conference on document analysis and recognition, ICDAR \u201909. IEEE Computer Society. Washington, DC, pp\u00a01\u20135"},{"key":"1250_CR10","doi-asserted-by":"crossref","unstructured":"Hua XS, Chen XY, Zhang HJ (2001) Automatic location of text in video frames. In: Proc. of ACM multimedia 2001 workshops: multimedia information retrieval, pp 24\u201327","DOI":"10.1145\/500933.500941"},{"key":"1250_CR11","doi-asserted-by":"crossref","unstructured":"Hua XS, Liu WY, Zhang HJ (2004) An automatic performance evaluation protocol for video text detection algorithms. IEEE Trans Circuits Syst Video Technol 14(4):498\u2013507","DOI":"10.1109\/TCSVT.2004.825538"},{"key":"1250_CR12","unstructured":"ICDAR RWR (2011) http:\/\/www.cvc.uab.es\/icdar2011competition\/?com=results (last access: 10\/07\/2012)"},{"issue":"5","key":"1250_CR13","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, Kim KI, Jain AK (2004) Text information extraction in images and video: a survey. Pattern Recogn 37(5):977\u2013997","journal-title":"Pattern Recogn"},{"key":"1250_CR14","doi-asserted-by":"crossref","unstructured":"Karatzas D, Mestre SR, Mas J, Nourbakhsh F, Roy PP (2011) Icdar 2011 robust reading competition: challenge 1: reading text in born-digital images (web and email). In: Proc. international conference on document analysis and recognition (ICDAR). Beijing, pp\u00a01485\u20131490","DOI":"10.1109\/ICDAR.2011.295"},{"key":"1250_CR15","unstructured":"Keysers D (2006) Comparison and combination of state-of-the-art techniques for handwritten character recognition: topping the mnist benchmark"},{"key":"1250_CR16","doi-asserted-by":"crossref","unstructured":"Kim HH (2011) Toward video semantic search based on a structured folksonomy. J Am Soc Inf Sci Technol 62(3):478\u2013492","DOI":"10.1002\/asi.21482"},{"issue":"2","key":"1250_CR17","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/S0031-3203(00)00095-9","volume":"34","author":"KI Kim","year":"2001","unstructured":"Kim KI, Jung K, Park SH, Kim HJ (2001) Support vector machine-based text detection in digital video. Pattern Recogn 34(2):527\u2013529","journal-title":"Pattern Recogn"},{"key":"1250_CR18","unstructured":"Li H, Kia O, Doermann D (1999) Text emhancement in digital video. In: Proc. of SPIE, document recognition IV, pp\u00a01\u20138"},{"issue":"1","key":"1250_CR19","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/83.817607","volume":"9","author":"H Li","year":"2000","unstructured":"Li H, Doermann DS, Kia OE (2000) Automatic text detection and tracking in digital video. IEEE Trans Image Process 9(1):147\u2013156","journal-title":"IEEE Trans Image Process"},{"key":"1250_CR20","doi-asserted-by":"crossref","unstructured":"Lienhart R, Wernicke A (2002) Localizing and segmenting text in images and videos. IEEE Trans Circuits Syst Video Technol 12(4):256\u2013268","DOI":"10.1109\/76.999203"},{"key":"1250_CR21","volume-title":"An introduction to digital image processing","author":"W Niblack","year":"1986","unstructured":"Niblack W (1986) An introduction to digital image processing. Prentice-Hall, Englewood Cliffs"},{"issue":"1","key":"1250_CR22","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","volume":"29","author":"T Ojala","year":"1996","unstructured":"Ojala T, Pietik\u00e4inen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recogn 29(1):51\u201359","journal-title":"Pattern Recogn"},{"issue":"1","key":"1250_CR23","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"19","author":"N Otsu","year":"1978","unstructured":"Otsu N (1978) A threshold selection method from gray level histogram. IEEE Trans Syst Man Cybern 19(1):62\u201366","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1250_CR24","doi-asserted-by":"crossref","unstructured":"Pan YF, Hou X, Liu CL (2008) A robust system to detect and localize texts in natural scene images. In: Proceedings of the 2008 the eighth IAPR international workshop on document analysis systems, DAS \u201908. IEEE Computer Society. Washington, DC, pp\u00a035\u201342","DOI":"10.1109\/DAS.2008.42"},{"key":"1250_CR25","doi-asserted-by":"crossref","unstructured":"Qian X, Liu G, Wang H, Su R (2007) Text detection, localization and tracking in compressed video. In: Proc. of international conference on signal processing: image communication, pp\u00a0752\u2013768","DOI":"10.1016\/j.image.2007.06.005"},{"issue":"5","key":"1250_CR26","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s005300050140","volume":"7","author":"T Sato","year":"1999","unstructured":"Sato T, Kanade T, Hughes EK, Smith MA, Satoh S (1999) Video OCR: indexing digital new libraries by recognition of superimposed captions. Multimedia Syst 7(5):385\u2013395","journal-title":"Multimedia Syst"},{"issue":"2","key":"1250_CR27","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, Pietikainen M (2000) Adaptive document image binarization. Pattern Recogn 33(2):225\u2013236","journal-title":"Pattern Recogn"},{"key":"1250_CR28","volume-title":"Image analysis and mathematical morphology","author":"J Serra","year":"1983","unstructured":"Serra J (1983) Image analysis and mathematical morphology. Academic Press, Orlando"},{"key":"1250_CR29","doi-asserted-by":"crossref","unstructured":"Shivakumara P, Phan TQ, Tan CL (2009) Video text detection based on filters and edge features. In: Proc. of the 2009 international conference on multimedia and expo. IEEE, pp 1\u20134","DOI":"10.1109\/ICME.2009.5202546"},{"key":"1250_CR30","unstructured":"Sobel I (1990) An isotropic 3\u00d73 image gradient operator. In: Machine version for three-dimentional scenes, pp 376\u2013379"},{"key":"1250_CR31","doi-asserted-by":"crossref","unstructured":"Sobottka K, Bunke H, Kronenberg H (1999) Identification of terxt on colored book and journal covers. In: Proc. of international conference on document analysis and recognition, pp 57\u201363","DOI":"10.1109\/ICDAR.1999.791724"},{"key":"1250_CR32","first-page":"1799","volume":"11","author":"S Sonnenburg","year":"2010","unstructured":"Sonnenburg S, R\u00e4tsch G, Henschel S, Widmer C, Behr J, Zien A, Bona, FD, Binder A, Gehl C, Franc V (2010) The shogun machine learning toolbox. J Mach Learn Res 11:1799\u20131802","journal-title":"J Mach Learn Res"},{"key":"1250_CR33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2007.01.001","volume":"107","author":"CM Thillou","year":"2007","unstructured":"Thillou CM, Gosselin B (2007) Color text extraction with selective metric-based clustering. Comput Vis Image Underst 107:1\u20132","journal-title":"Comput Vis Image Underst"},{"key":"1250_CR34","doi-asserted-by":"crossref","unstructured":"Wolf C, Jolion JM, Chassaing F (2002) Text localization, enhancement and binarization in multimedia documents. In: Proc. of the international conference on pattern recognition, vol\u00a02, pp 1037\u20131040","DOI":"10.1109\/ICPR.2002.1048482"},{"key":"1250_CR35","doi-asserted-by":"crossref","unstructured":"Yang H, Siebert M, L\u00fchner P, Sack H, Meinel C (2011) Automatic lecture video indexing using video OCR technology. In: Proc. of international symposium on multimedia (ISM), pp 111\u2013116","DOI":"10.1109\/ISM.2011.26"},{"key":"1250_CR36","doi-asserted-by":"crossref","unstructured":"Zeng C, Ma H (2010) Robust head-shoulder detection by pca-based multilevel hog-lbp detector for people counting. In: Proceedings of the 2010 20th international conference on pattern recognition, ICPR \u201910. IEEE Computer Society. Washington, DC, pp 2069\u20132072","DOI":"10.1109\/ICPR.2010.509"},{"key":"1250_CR37","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1016\/j.imavis.2010.04.002","volume":"28","author":"M Zhao","year":"2010","unstructured":"Zhao M, Li S, Kwok J (2010) Text detection in images using sparse representation with discriminative dictionaries. J Image Vis Comput 28:1590\u20131599","journal-title":"J Image Vis Comput"},{"key":"1250_CR38","doi-asserted-by":"crossref","unstructured":"Zhong Y, Zhang HJ, Jain A (2000) Automatic caption localization in compressed video. IEEE Trans Pattern Anal Mach Intell 22(4):385\u2013392","DOI":"10.1109\/34.845381"},{"key":"1250_CR39","doi-asserted-by":"crossref","unstructured":"Zhou Z, Li L, Tan CL (2010) Edge based binarization for video text images. In: Proc. of 20th international conference on pattern recognition. Singapore, pp 133\u2013136","DOI":"10.1109\/ICPR.2010.41"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1250-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-012-1250-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1250-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T04:48:28Z","timestamp":1643518108000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-012-1250-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,11]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["1250"],"URL":"https:\/\/doi.org\/10.1007\/s11042-012-1250-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,10,11]]}}}