{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:40:23Z","timestamp":1775281223272,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2010,11,9]],"date-time":"2010-11-09T00:00:00Z","timestamp":1289260800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2011,2]]},"DOI":"10.1007\/s10462-010-9187-5","type":"journal-article","created":{"date-parts":[[2010,11,8]],"date-time":"2010-11-08T16:04:52Z","timestamp":1289232292000},"page":"119-136","source":"Crossref","is-referenced-by-count":27,"title":["A survey of keyword spotting techniques for printed document images"],"prefix":"10.1007","volume":"35","author":[{"given":"Abirami","family":"Murugappan","sequence":"first","affiliation":[]},{"given":"Baskaran","family":"Ramachandran","sequence":"additional","affiliation":[]},{"given":"P.","family":"Dhavachelvan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,11,9]]},"reference":[{"key":"9187_CR1","doi-asserted-by":"crossref","unstructured":"Abirami S, Manjula D (2009) Feature string based intelligent information retrieval from tamil document images. Int J Comput Appl Technol Special Issue on \u2018Computer Applications in Knowledge Based Systems\u2019, Vol. 35, No. 2\/3\/4. Inderscience Publishers, pp 150\u2013164","DOI":"10.1504\/IJCAT.2009.026592"},{"key":"9187_CR2","unstructured":"Aparna KH, Chakravarthi VS (2003) A complete OCR system development of OCR Tamil magazine documents. Tamil Internet"},{"key":"9187_CR3","first-page":"1","volume":"3872","author":"A Balasubramanian","year":"2006","unstructured":"Balasubramanian A, Meshesha M, Jawahar CV (2006) Retrieval from document image collections. In: Proceedings of the international workshop on document analysis systems, LNCS 3872: 1\u201312","journal-title":"In: Proceedings of the international workshop on document analysis systems, LNCS"},{"key":"9187_CR4","unstructured":"Balasubramanian A, Jawahar CV (2006) Textual search in graphics stream of PDF. International conference on digital libraries, pp 1\u201310"},{"key":"9187_CR5","doi-asserted-by":"crossref","unstructured":"Chaudhury S, Sethi G, Vyas A, Harit G (2003) Devising interactive access techniques for indian language document images. In: Proceedings of the seventh international conference on document analysis and recognition, pp 885\u2013889","DOI":"10.1109\/ICDAR.2003.1227787"},{"key":"9187_CR6","doi-asserted-by":"crossref","unstructured":"Chen FR, Wilcox LD, Bloomberg DS (1993) Detecting and locating partially specified keywords in scanned images using hidden markov models. In: Proceedings of the international conference on document analysis and recognition, pp 133\u2013138","DOI":"10.1109\/ICDAR.1993.395765"},{"key":"9187_CR7","doi-asserted-by":"crossref","unstructured":"Chen FR, Wilcox LD, Bloomberg DS (1995) A comparison of discrete and continuous hidden markov models for phrase spotting in text images. In: Proceedings of the international conference on document analysis and recognition, pp 398\u2013402","DOI":"10.1109\/ICDAR.1995.599022"},{"key":"9187_CR8","unstructured":"Chen FR, Bloomberg DS (1996) Extraction of thematically relevant text from images. Symposium on document analysis and information retrieval, pp 163\u2013178"},{"issue":"3","key":"9187_CR9","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1006\/cviu.1998.0692","volume":"70","author":"D Doermann","year":"1998","unstructured":"Doermann D (1998) Indexing and retrieval of document images: a survey. J Comput Vis Image Underst 70(3): 287\u2013298","journal-title":"J Comput Vis Image Underst"},{"key":"9187_CR10","doi-asserted-by":"crossref","unstructured":"Harit G, Chaudhury S, Ghosh H (2004) Managing document images in a digital library: an ontology guided approach. In: Proceedings of the first international workshop on document image analysis for libraries, pp 64\u201392","DOI":"10.1109\/DIAL.2004.1263238"},{"key":"9187_CR11","doi-asserted-by":"crossref","unstructured":"Harit G, Chaudhury S, Gupta P, Vohra N, Joshi SD (2001) Model guided document image analysis system. In: Proceedings of the sixth international conference on document analysis and recognition, pp 1137\u20131141","DOI":"10.1109\/ICDAR.2001.953963"},{"key":"9187_CR12","doi-asserted-by":"crossref","unstructured":"Harit G, Chaudhury S, Paranjpe J (2005) Ontology guided access to document images. In: Proceedings of the eighth international conference on document analysis and recognition, pp 292\u2013296","DOI":"10.1109\/ICDAR.2005.181"},{"key":"9187_CR13","doi-asserted-by":"crossref","unstructured":"Harit G, Garg R, Chaudhury S (2007) An integrated scheme for compression and interactive access to document images. In: Proceedings of the international conference on computing: theory and applications, pp 506\u2013511","DOI":"10.1109\/ICCTA.2007.29"},{"key":"9187_CR14","doi-asserted-by":"crossref","unstructured":"Harit G, Jain R, Chaudhury S (2005) Improved geometric feature graph: a script independent representation of word images for compression and retrieval. In: Proceedings of the eighth international conference on document analysis and recognition, pp 421\u2013425","DOI":"10.1109\/ICDAR.2005.136"},{"key":"9187_CR15","unstructured":"Jawahar CV, Meshesha M, Balasubramanian A (2004) Searching in document images. In: Proceedings of the international conference on visualization, graphics and image processing, pp 622\u2013627"},{"key":"9187_CR16","unstructured":"Jawahar CV, Million M, Balasubramanian A (2004) Word level access to document image datasets. In: Proceedings of the workshop on computer vision, graphics and image processing, pp 73\u201376"},{"key":"9187_CR17","doi-asserted-by":"crossref","unstructured":"Kameshiro T, Hirano T, Okada Y, Yoda F (1999) A document image retrieval method tolerating recognition and segmentation errors of OCR using shape feature and multiple candidates. In: Proceedings of the fifth international conference on document analysis and recognition, pp 681\u2013684","DOI":"10.1109\/ICDAR.1999.791879"},{"issue":"Part. 1","key":"9187_CR18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/BF02703309","volume":"27","author":"R Kasthuri","year":"2002","unstructured":"Kasthuri R, Gormann LO, Govindaraju V (2002) Document image aanlysis: a primer. Sadhana 27(Part. 1): 3\u201322","journal-title":"Sadhana"},{"key":"9187_CR19","first-page":"57","volume":"4670","author":"K Katsuyama","year":"2002","unstructured":"Katsuyama K (2002) Highly accurate retrieval of Japanese document images through a combination of morphological analysis and OCR. In: Proceedings of the document recognition and retrieval 4670: 57\u201367","journal-title":"In: Proceedings of the document recognition and retrieval"},{"key":"9187_CR20","unstructured":"Krishnamoorthy V (2002) OCR software for Tamil Printed Text. Tamil Internet, pp 99\u2013102"},{"issue":"11","key":"9187_CR21","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1109\/TPAMI.2008.89","volume":"30","author":"S Lu","year":"2008","unstructured":"Lu S, Linlin L, Tan CL (2008) Document Image Retrieval through Word Shape Coding. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(11): 1913\u20131918","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9187_CR22","doi-asserted-by":"crossref","unstructured":"Lu S, Tan CL (2007) Keyword Spotting and Retrieval of Document Images captured by a Digital Camera. In: Proceedings of the ninth international conference on document analysis and recognition, pp 994\u2013998","DOI":"10.1109\/ICDAR.2007.4377064"},{"key":"9187_CR23","unstructured":"Lu Y, Tan CL, Huang W, Fan L (2001a) An approach to word image matching based on weighted Hausdorff distance. In: Proceedings of the international conference on document analysis and recognition, pp 921\u2013925"},{"key":"9187_CR24","unstructured":"Lu Y, Tan CL, Fan L, Huang W (2001b) Similarity measure for CCITT group 4 compressed document images. In: Proceedings of the international conference on image processing, pp 1118\u20131121"},{"key":"9187_CR25","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-45869-7_37","volume":"2423","author":"Y Lu","year":"2002","unstructured":"Lu Y, Tan CL (2002a) \u2018Word Searching in Document Images Using Word Portion Matching\u2019. Document Analysis Systems V, Lecture Notes on Computer science 2423: 319\u2013328","journal-title":"Document Analysis Systems V, Lecture Notes on Computer science"},{"key":"9187_CR26","unstructured":"Lu Y, Tan CL (2002b) Word spotting in Chinese document images without layout analysis. In: Proceedings of the international conference on pattern recognition, pp 57\u201360"},{"key":"9187_CR27","doi-asserted-by":"crossref","unstructured":"Lu Y, Tan CL (2003) Word searching in CCITT group 4 compressed document images. International conference on document analysis and recognition, pp 467\u2013471","DOI":"10.1109\/ICDAR.2003.1227709"},{"issue":"11","key":"9187_CR28","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1109\/TKDE.2004.76","volume":"16","author":"Y Lu","year":"2004","unstructured":"Lu Y, Tan CL (2004) Information Retrieval in Document Image Databases. IEEE Transactions on Knowledge and Data Engineering 16(11): 1398\u20131410","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"9187_CR29","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1142\/S0218001404003137","volume":"18","author":"Y Lu","year":"2004","unstructured":"Lu Y, Tan CL (2004) Chinese Word searching in Imaged documents. International Journal of Pattern Recognition and Artificial Intelligence 18(2): 229\u2013246","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"9187_CR30","unstructured":"Lu Y, Zhang L, Tan CL (2004a) Retrieved Imaged documents in digital libraries based on Word Imaged Coding. In: Proceedings of the first international workshop on document image analysis for libraries, pp 174\u2013187"},{"key":"9187_CR31","doi-asserted-by":"crossref","unstructured":"Lu Y, Zhang L, Tan CL (2004b) A Search engine for Imaged documents in PDF files. In; Proceedings of the special interest group on information retrieval, pp 536\u2013537","DOI":"10.1145\/1008992.1009108"},{"key":"9187_CR32","unstructured":"Nagy G, Seth S (1984) Hierarchical representation of optically scanned documents. In: Proceedings of the international conference on pattern recognition, pp 347\u201334"},{"key":"9187_CR33","doi-asserted-by":"crossref","unstructured":"Ohtam M, Takasu A, Adachi J (1997) Retrieval Methods for English Text with Misrecognized OCR characters. In: Proceedings of the fourth international conference on document analysis and recognition, pp 950\u2013956","DOI":"10.1109\/ICDAR.1997.620651"},{"key":"9187_CR34","first-page":"837","volume":"4338","author":"K Pramod Shankar","year":"2006","unstructured":"Pramod Shankar K, Jawahar CV (2006) Enabling Search over Large Collections of Telugu Document Images- An automatic Annotation based approach. LNCS 4338: 837\u2013848","journal-title":"LNCS"},{"key":"9187_CR35","doi-asserted-by":"crossref","unstructured":"Rath T, Manmatha R (2003) Features for word spotting in historical manuscripts. International conference on document analysis and recognition, pp 218\u2013222","DOI":"10.1109\/ICDAR.2003.1227662"},{"issue":"11","key":"9187_CR36","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1631\/jzus.2005.A1297","volume":"6","author":"R Seethalakshmi","year":"2005","unstructured":"Seethalakshmi R, SreeRanjani TR, Balachandar T, Abnikant Singh, Markandey S, Ritwaj R, Sarvesh K (2005) Optical Character Recognition for printed Tamil text using Unicode. Journal of Zhejiang University Science 6(11): 1297\u20131305","journal-title":"Journal of Zhejiang University Science"},{"key":"9187_CR37","unstructured":"Smeaton AF, Spitz AL (1997) Using Character shape codes for information retrieval. In: Proceedings of the international conference on document analysis and recognition, pp 974\u2013978"},{"key":"9187_CR38","unstructured":"Spitz AL (1993) Generalized line, word and character finding. In: Proceedings of the progress in image analysis and processing, pp 377\u2013383"},{"key":"9187_CR39","unstructured":"Spitz AL (1995) Using character shape codes for word spotting in document images. In: Proceedings of the symposium on document analysis and information retrieval, pp 382\u2013389"},{"issue":"3","key":"9187_CR40","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/34.584100","volume":"19","author":"AL Spitz","year":"1997","unstructured":"Spitz AL (1997) Determination of script, language content of document images. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(3): 235\u2013245","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9187_CR41","unstructured":"Subramanian A, Kuberan B (2000) Optical Character Recognition of Printed Tamil characters. In: Proceedings of the tamil internet conference"},{"key":"9187_CR42","unstructured":"Tan CL, Sung SY, Yu Z, Xu Y (2000) Text retrieval from document images based on n-gram algorithm. In: Proceedings of the sixth pacific rim international conference on artificial intelligence, pp 1\u201312"},{"issue":"6","key":"9187_CR43","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1109\/TPAMI.2002.1008389","volume":"24","author":"CL Tan","year":"2002","unstructured":"Tan CL, Huang W, Yu Z, Xu Y (2002) Imaged Document Text retrieval without OCR. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(6): 838\u2013844","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"9187_CR44","first-page":"257","volume":"18","author":"CL Tan","year":"2003","unstructured":"Tan CL, Huang W, Sung SY, Yu Z, Xu X (2003) Text retrieval from document images based on word shape analysis. Journal of Applied Intelligence, Special issue on Text and Web Mining 18(3): 257\u2013270","journal-title":"Journal of Applied Intelligence, Special issue on Text and Web Mining"},{"key":"9187_CR45","unstructured":"Tanaka Y, Torii H (1988) Transmedia machine and its keyword search over image texts. In: Proceedings of the research information assistee par ordinateur, pp 248\u2013258"},{"key":"9187_CR46","unstructured":"Zhang L, Lu Y, Tan CL (2004) A web based system for retrieving document images from digital library. In: Proceedings of the conference on computer vision and pattern recognition workshop, pp 27\u201335"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-010-9187-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-010-9187-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-010-9187-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T04:10:50Z","timestamp":1559794250000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-010-9187-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11,9]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,2]]}},"alternative-id":["9187"],"URL":"https:\/\/doi.org\/10.1007\/s10462-010-9187-5","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,11,9]]}}}