{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T04:02:25Z","timestamp":1747627345556,"version":"3.40.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:00:00Z","timestamp":1051747200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:00:00Z","timestamp":1051747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Intelligence"],"published-print":{"date-parts":[[2003,5]]},"DOI":"10.1023\/a:1023245904128","type":"journal-article","created":{"date-parts":[[2003,6,6]],"date-time":"2003-06-06T17:39:54Z","timestamp":1054921194000},"page":"257-270","source":"Crossref","is-referenced-by-count":11,"title":["Text Retrieval from Document Images Based on Word Shape Analysis"],"prefix":"10.1007","volume":"18","author":[{"given":"Chew Lim","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sam Yuan","family":"Sung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5119081_CR1","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1126\/science.253.5023.974","volume":"253","author":"G. Salton","year":"1991","unstructured":"G. Salton, \u201cDevelopments in automatic text retrieval,\u201d Science, vol. 253, pp. 974\u2013980, 1991.","journal-title":"Science"},{"key":"5119081_CR2","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1126\/science.253.5023.1012","volume":"253","author":"G. Salton","year":"1991","unstructured":"G. Salton and C. Buckley, \u201cGlobal text matching for information retrieval,\u201d Science, vol. 253, pp. 1012\u20131015, 1991.","journal-title":"Science"},{"key":"5119081_CR3","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1126\/science.264.5164.1421","volume":"264","author":"G. Salton","year":"1994","unstructured":"G. Salton, J. Allan, C. Buckley, and A. Singhal, \u201cAutomatic analysis, theme generation, and summarization of machine-readable text,\u201d Science, vol. 264, pp. 1421\u20131426, 1994.","journal-title":"Science"},{"key":"5119081_CR4","volume-title":"The Mathematical Theory of Communication","author":"C.E. Shannon","year":"1949","unstructured":"C.E. Shannon, The Mathematical Theory of Communication, University of Illinois Press: Urbana, 1949."},{"issue":"2","key":"5119081_CR5","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/TPAMI.1979.4766902","volume":"1","author":"C.Y. Suen","year":"1979","unstructured":"C.Y. Suen, \u201cN-gram statistics for natural language understanding and text processing,\u201d IEEE Trans. on Pattern Analysis & Machine Intelligence, PAMI, vol. 1, no.2, pp. 164\u2013172, 1979.","journal-title":"IEEE Trans. on Pattern Analysis & Machine Intelligence, PAMI"},{"doi-asserted-by":"crossref","unstructured":"A. Zamora, \u201cAutomatic detection and correcting of spelling errors in a large data base,\u201d Journal of the American Society for Information Science, vol. 31, no.51, 1980.","key":"5119081_CR6","DOI":"10.1002\/asi.4630310106"},{"key":"5119081_CR7","first-page":"676","volume":"ACM23","author":"J.L. Peterson","year":"1980","unstructured":"J.L. Peterson, \u201cComputer programs for detecting and correcting spelling errors,\u201d Comm. vol. ACM 23, p. 676, 1980.","journal-title":"Comm."},{"key":"5119081_CR8","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/0306-4573(81)90044-3","volume":"17","author":"E.M. Zamora","year":"1981","unstructured":"E.M. Zamora, J.J. Pollock, and A. Zamora, \u201cThe use of trigram analysis for spelling error detection,\u201d Inf. Proc. Mgt. vol. 17, p. 305, 1981.","journal-title":"Inf. Proc. Mgt."},{"key":"5119081_CR9","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1109\/TPAMI.1982.4767297","volume":"PAMI-4","author":"J.J. Hull","year":"1980","unstructured":"J.J. Hull and S.N. Srihari, \u201cExperiments in text recognition with binary N-gram and Viterbi algorithms,\u201d IEEE Trans. Pattern Analysis & Machine Intelligence, vol. PAMI-4, p. 520, 1980.","journal-title":"IEEE Trans. Pattern Analysis & Machine Intelligence"},{"key":"5119081_CR10","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1108\/eb026733","volume":"38","author":"J.J. Pollock","year":"1982","unstructured":"J.J. Pollock, \u201cSpelling error detection and correction by computer: Some notes and a bibliography,\u201d J. Doc. vol. 38, p. 282, 1982.","journal-title":"J. Doc."},{"key":"5119081_CR11","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/0306-4573(83)90022-5","volume":"18","author":"R.C. Angell","year":"1983","unstructured":"R.C. Angell, G.E. Freund, and P. Willette, \u201cAutomatic spelling correction using trigram similarity measure,\u201d Inf. Proc. Mgt. vol. 18, p. 255, 1983.","journal-title":"Inf. Proc. Mgt."},{"key":"5119081_CR12","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/0306-4573(82)90047-4","volume":"18","author":"E.J. Yannakoudakis","year":"1982","unstructured":"E.J. Yannakoudakis, P. Goyal, and J.A. Huggill, \u201cThe generation and use of text fragments for data compression,\u201d Inf. Proc. Mgt. vol. 18, p. 15, 1982.","journal-title":"Inf. Proc. Mgt."},{"unstructured":"J.C. Schmitt, \u201cTrigram-based method of language identification,\u201d U.S. Patent No. 5,062,143, 1990.","key":"5119081_CR13"},{"unstructured":"W.B. Cavnar and J.M. Trenkle, \u201cN-gram-based text categorization,\u201d in Proceeding of the Symposium on Document Analysis and Information Retrieval, University of Nevada, Las Vegas, 1994.","key":"5119081_CR14"},{"key":"5119081_CR15","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1108\/eb026684","volume":"35","author":"P. Willett","year":"1979","unstructured":"P. Willett, \u201cDocument retrieval experiments using indexing vocabularies of varying size. II. Hashing, Truncation. Digram and trigram encoding of index terms,\u201d J. Doc. vol. 35, p. 296, 1979.","journal-title":"J. Doc."},{"key":"5119081_CR16","series-title":"NIST Special Publication","volume-title":"The Second Text Retrieval Conference (TREC-2)","author":"W.B. Cavnar","year":"1994","unstructured":"W.B. Cavnar, \u201cN-gram-based text filtering for TREC-2,\u201d The Second Text Retrieval Conference (TREC-2), NIST Special Publication 500-215, National Institute of Standards and Technology, Gaitherburg, Maryland, 1994."},{"key":"5119081_CR17","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M. Damashek","year":"1995","unstructured":"Marc Damashek, \u201cGauging similarity via N-grams: Language-independent sorting, categorization, and retrieval of text,\u201d Science, vol. 267, pp. 843\u2013848, 1995.","journal-title":"Science"},{"doi-asserted-by":"crossref","unstructured":"S.M. Harding, W.B. Croft, and C. Weir, \u201cProbabilistic retrieval of OCR degraded text using N-grams,\u201d in European Conference on Digital Libraries, pp. 345\u2013359, 1997.","key":"5119081_CR18","DOI":"10.1007\/BFb0026737"},{"unstructured":"W.B. Croft, S.M. Harding, K. Taghva, and J. Borsack, \u201cAn evaluation of information retrieval accuracy with simulated OCR output,\u201d in Symposium of Document Analysis and Information Retrieval, pp. 115\u2013126, 1994.","key":"5119081_CR19"},{"unstructured":"F.R. Chen and D.S. Bloomberg, \u201cExtraction of thematically relevant text from images,\u201d in Proceedings of the Symposium on Document Analysis and Information Retrieval, pp. 163\u2013178, 1996.","key":"5119081_CR20"},{"key":"5119081_CR21","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1109\/ICDAR.1997.619846","volume":"1","author":"F.R. Chen","year":"1997","unstructured":"F.R. Chen and D.S. Bloomberg, \u201cExtraction of indicative summary sentences from imaged documents,\u201d in Proceedings of the Fourth International Conference on Document Analysis and Recognition (ICDAR\u201997), vol. 1, pp. 227\u2013232, 1997.","journal-title":"Proceedings of the Fourth International Conference on Document Analysis and Recognition (ICDAR\u201997)"},{"key":"5119081_CR22","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/ICDAR.1997.619862","volume":"1","author":"J.J. Hull","year":"1997","unstructured":"J.J. Hull and J.F. Cullen, \u201cDocument image similarity and equivalence detection,\u201d in Proceedings of the Fourth International Conference on Document Analysis and Recognition (ICDAR\u201997), vol. 1, pp. 308\u2013312, 1997.","journal-title":"Proceedings of the Fourth International Conference on Document Analysis and Recognition (ICDAR\u201997)"},{"doi-asserted-by":"crossref","unstructured":"Y. He, Z. Jiang, B. Liu, and H. Zhao, \u201cContent-based indexing and retrieval method of chinese document images,\u201d in Proceedings of the Fifth International Conference on Document Analysis and Recognition (ICDAR\u201999), pp. 685\u2013688, 1999.","key":"5119081_CR23","DOI":"10.1109\/ICDAR.1999.791880"},{"doi-asserted-by":"crossref","unstructured":"P. Sibun and A.L. Splitz, \u201cLanguage determination: National language processing from scanned document images,\u201d in Proceedings of the fourth Conference on Applied Natural Language Processing, pp. 423\u2013433, Las Vegas, April 1995.","key":"5119081_CR24","DOI":"10.3115\/974358.974363"},{"issue":"3","key":"5119081_CR25","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/34.584100","volume":"19","author":"A.L. Spitz","year":"1997","unstructured":"A.L. Spitz, \u201cDetermination of the script and language content of document images,\u201d IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, no.3, pp. 235\u2013245, 1997.","journal-title":"IEEE Trans. on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"C.Y. Suen, S. Bergler, N. Nobile, B. Waked, C.P. Nadal, and A. Bloch, \u201cCategorizing document images into script and language classes,\u201d in Proceedings of the International Conference on Advances in Pattern Recognition, Plymouth, UK, pp. 297\u2013306, 23\u201325 Nov 1998.","key":"5119081_CR26","DOI":"10.1007\/978-1-4471-0833-7_30"},{"unstructured":"C.L. Tan, P.Y. Leong, and S. He, \u201cLanguage identification in multilingual documents,\u201d in International Symposium on Intelligent Multimedia and Distance Education, 1999.","key":"5119081_CR27"},{"key":"5119081_CR28","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1109\/ICDAR.1997.620655","volume":"2","author":"A.F. Smeaton","year":"1997","unstructured":"A.F. Smeaton and A.L. Spitz, \u201cUsing character shape coding for information retrieval,\u201d in Proceeding of the Fourth International Conference on Document Analysis and Recognition (ICDAR97), vol. 2, pp. 974\u2013978, 1997.","journal-title":"Proceeding of the Fourth International Conference on Document Analysis and Recognition (ICDAR97)"},{"issue":"3","key":"5119081_CR29","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/S0031-3203(96)00093-3","volume":"30","author":"R.K. Powalka","year":"1997","unstructured":"R.K. Powalka, N. Sherkat, and R.J. Whitrow, \u201cWord shape analysis for a hybrid recognition system,\u201dPattern Recognition, vol. 30, no.3, pp. 421\u2013445, 1997.","journal-title":"Pattern Recognition"},{"unstructured":"D.S. Bloomberg, G.E. Kopec, and L. Dasari, \u201cMeasuring document image skew and orientation,\u201d SPIE Conf. 2422, Document Recognition II, San Jose, CA, pp. 302\u2013316, 1995.","key":"5119081_CR30"},{"doi-asserted-by":"crossref","unstructured":"Y. Yang and X. Liu, \u201cA re-examination of text categorization methods,\u201d in Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 42\u201349, 1999.","key":"5119081_CR31","DOI":"10.1145\/312624.312647"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1023245904128.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1023245904128\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1023245904128.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T14:52:28Z","timestamp":1747579948000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1023245904128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,5]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2003,5]]}},"alternative-id":["5119081"],"URL":"https:\/\/doi.org\/10.1023\/a:1023245904128","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2003,5]]}}}