{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:25:42Z","timestamp":1780053942745,"version":"3.54.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2005,4,1]],"date-time":"2005-04-01T00:00:00Z","timestamp":1112313600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2005,4]]},"DOI":"10.1007\/s00530-004-0159-y","type":"journal-article","created":{"date-parts":[[2005,2,3]],"date-time":"2005-02-03T09:20:53Z","timestamp":1107422453000},"page":"344-355","source":"Crossref","is-referenced-by-count":19,"title":["Caption analysis and recognition for building video indexing systems"],"prefix":"10.1007","volume":"10","author":[{"given":"Fu","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guey-Ching","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Chin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Hsiung","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"159_CR1","doi-asserted-by":"crossref","unstructured":"Antani S, Crandall D, Kasturi R (2000) Robust extraction of text in video. In: Proceedings of the IEEE international conference on pattern recognition, 1:831-834","DOI":"10.1109\/ICPR.2000.905537"},{"key":"159_CR2","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/69.755615","volume":"11","author":"Aslandogan","year":"1999","unstructured":"Aslandogan YA, Yu CT (1999) Techniques and systems for image and video retrieval. IEEE Trans Knowl Data Eng 11:56-63","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"159_CR3","unstructured":"Chang CC, Lin CJ (2001b) LIBSVM - A library for support vector machines. http:\/\/www.csie.edu.tw\/~cjlin\/libsvm\/"},{"key":"159_CR4","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1007\/PL00013573","volume":"4","author":"Chang","year":"2001","unstructured":"Chang F (2001) Retrieving information from document images: problems and solutions. Int J Doc Anal Recog 4:46-55","journal-title":"Int J Doc Anal Recog"},{"key":"159_CR5","doi-asserted-by":"crossref","unstructured":"Chang F, Liang KH, Tan TM, Hwang WL (1999) Binarization of document images using Hadamard multiresolution analysis. In: 5th international conference on document analysis and recognition, Bangalore, India","DOI":"10.1109\/ICDAR.1999.791748"},{"key":"159_CR6","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.cviu.2003.09.002","volume":"93","author":"Chang","year":"2004","unstructured":"Chang F, Chen CJ, Lu CJ (2004) A linear-time component-labeling algorithm using contour tracing technique. Comput Vis Image Understand 93:206-220","journal-title":"Comput Vis Image Understand"},{"key":"159_CR7","unstructured":"Dasarathy BV (1991) NN concepts and techniques, nearest neighbor (NN) norms: NN pattern classification techniques. IEEE Press, New York, pp 1-30"},{"key":"159_CR8","doi-asserted-by":"crossref","unstructured":"Doermann D, Liang J, Li H (2003) Progress in camera-based document image analysis. In: Proceedings of the IEEE international conference on document analysis and recognition, pp 606-616","DOI":"10.1109\/ICDAR.2003.1227735"},{"key":"159_CR9","unstructured":"Hua XS, Yin P, Zhang HJ (2002) Efficient video text recognition using multiple frame integration. In: Proceedings of the IEEE international conference on image processing, 2:397-400"},{"key":"159_CR10","doi-asserted-by":"crossref","unstructured":"Jain AK, Yu B (1998) Automatic text location in images and video frames. In: Proceedings of the IEEE international conference on pattern recognition, 2:1497-1499","DOI":"10.1109\/ICPR.1998.711990"},{"key":"159_CR11","doi-asserted-by":"crossref","unstructured":"Kamada H, Fujimoto K (1999) High-speed, High-accuracy binarization method for recognizing text in images of low spatial resolutions. In Proceedings of the 5th international conference on document analysis and recognition, pp 139-142","DOI":"10.1109\/ICDAR.1999.791744"},{"key":"159_CR12","unstructured":"Kim EY, Kim KI, Jung K, Kim HJ (2000) A video indexing system using character recognition. In: Proceedings of the international conference on consumer electronics, pp 358-359"},{"key":"159_CR13","doi-asserted-by":"crossref","unstructured":"Knerr S, Personnaz L, and Dreyfus G (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: Neurocomputing: algorithms, architectures and applications. Springer, Berlin Heidelberg New York","DOI":"10.1007\/978-3-642-76153-9_5"},{"key":"159_CR14","doi-asserted-by":"crossref","unstructured":"Kuwano H, Taniguchi Y, Arai H, Mori M, Kurakake S, Kojima H (2000) Telop-on-demand: video structuring and retrieval based on text recognition. In: Proceedings of the IEEE international conference on multimedia and expo, 2:759-762","DOI":"10.1109\/ICME.2000.871472"},{"key":"159_CR15","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/34.506415","volume":"18","author":"Lee","year":"1996","unstructured":"Lee SW, Lee DJ, Park HS (1996) A new methodology for gray-scale character segmentation and recognition. IEEE Trans Pattern Anal Mach Intell 18:1045-1050","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"159_CR16","first-page":"19","volume":"1","author":"Li","year":"1999","unstructured":"Li H, Doermann D (1999) Text enhancement in digital video using multiple frame integration. ACM Multimedia 1:19-22","journal-title":"ACM Multimedia"},{"key":"159_CR17","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/83.817607","volume":"9","author":"Li","year":"2000","unstructured":"Li H, Doermann D, Kia O (2000) Automatic text detection and tracking in digital video. IEEE Trans Image Process 9:147-156","journal-title":"IEEE Trans Image Process"},{"key":"159_CR18","first-page":"a","volume":"OCR","author":"Lienhart","year":"2003","unstructured":"Lienhart R (2003) Video OCR: a survey and practitioner\u2019s guide. Kluwer, Dordrecht","journal-title":"Video"},{"key":"159_CR19","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s005300050006","volume":"8","author":"Lienhart","year":"2000","unstructured":"Lienhart R, Effelsberg W (2000) Automatic text segmentation and text recognition for video indexing. Multimedia Syst 8:69-81","journal-title":"Multimedia Syst"},{"key":"159_CR20","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/76.999203","volume":"12","author":"Lienhart","year":"2002","unstructured":"Lienhart R, Wernicke A (2002) Localizing and segmenting text in images and videos. IEEE Trans Circuits Syst Video Technol 12:256-268","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"159_CR21","first-page":"11","volume":"6","author":"Lin","year":"2001","unstructured":"Lin CJ, Liu CC, Chen HH (2001) A simple method for Chinese video OCR and its application to question answering. Int J Comput Linguist Chinese Lang Process 6:11-30","journal-title":"Int J Comput Linguist Chinese Lang Process"},{"key":"159_CR22","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0031-3203(94)00068-W","volume":"28","author":"Lu","year":"1995","unstructured":"Lu Y (1995) Machine printed character segmentation - an overview. Pattern Recog 28:67-80","journal-title":"Pattern Recog"},{"key":"159_CR23","doi-asserted-by":"crossref","unstructured":"Mita T, Hori O (2001) Improvement of video text recognition by character selection. In: Proceedings of the IEEE international conference on document analysis and recognition, pp 1089-1093","DOI":"10.1109\/ICDAR.2001.953954"},{"key":"159_CR24","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"1","author":"Otsu","year":"1979","unstructured":"Otsu N (1979) A threshold selection method from gray-scale histograms. IEEE Trans Syst Man Cybern 1:62-66","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"159_CR25","unstructured":"Platt JC, Cristianini N, Shawe-Taylor J (2000) Large margin DAG\u2019s for multiclass classification. In: Advances in neural information processing systems. MIT Press, Cambridge, MA, pp 547-553"},{"key":"159_CR26","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s005300050140","volume":"7","author":"Sato","year":"1999","unstructured":"Sato T, Kanade T, Hughes EK, Smith MA, Satoh S (1999) Video OCR: indexing digital news libraries by recognition of superimposed captions. Multimedia Syst 7:385-395","journal-title":"Multimedia Syst"},{"key":"159_CR27","doi-asserted-by":"crossref","unstructured":"Smith MA, Kanade T (1997) Video skimming and characterization through the combination of image and language understanding techniques. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Puerto Rico, pp 775-781","DOI":"10.1109\/CVPR.1997.609414"},{"key":"159_CR28","unstructured":"Shim JC, Dorai C, Bolle R (1998) Automatic text extraction from video for content-based annotation and retrieval. In: Proceedings of the international conference on pattern recognition, 1:16-20"},{"key":"159_CR29","doi-asserted-by":"crossref","unstructured":"Vapnik V (1995) The nature of statistical learning theory. Springer, Berlin Heidelberg New York","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"159_CR30","doi-asserted-by":"crossref","unstructured":"Wong EK, Chen M (2000) A robust algorithm for text extraction in color video. In: IEEE international conference on multimedia and expo, 2:797-800","DOI":"10.1109\/ICME.2000.871481"},{"key":"159_CR31","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/34.809116","volume":"21","author":"Wu","year":"1999","unstructured":"Wu V, Manmatha R, Riseman EM (1999) TextFinder: an automatic system to detect and recognize text in images. IEEE Trans Pattern Anal Mach Intell 21:1224-1229","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-004-0159-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-004-0159-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-004-0159-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T02:25:24Z","timestamp":1559096724000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-004-0159-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,4]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2005,4]]}},"alternative-id":["159"],"URL":"https:\/\/doi.org\/10.1007\/s00530-004-0159-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,4]]}}}