{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:09:50Z","timestamp":1775282990127,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,4,16]],"date-time":"2009-04-16T00:00:00Z","timestamp":1239840000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2009,7]]},"DOI":"10.1007\/s10032-009-0081-0","type":"journal-article","created":{"date-parts":[[2009,4,15]],"date-time":"2009-04-15T15:02:47Z","timestamp":1239807767000},"page":"65-81","source":"Crossref","is-referenced-by-count":52,"title":["Automated analysis of images in documents for intelligent document search"],"prefix":"10.1007","volume":"12","author":[{"given":"Xiaonan","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saurabh","family":"Kataria","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William J.","family":"Brouwer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James Z.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasenjit","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,4,16]]},"reference":[{"key":"81_CR1","unstructured":"Antani, S., Gargi, U., Crandall, D., Gandhi, T., Kasturi, R.: Extraction of text in video. Technical Report, Department of Computer Science and Engineering, Pennsylvania State University, CSE-99-016 August 30 (1999)"},{"key":"81_CR2","doi-asserted-by":"crossref","unstructured":"Blostein, D., Lank, E., Zanibbi, R.: Treatment of diagrams in document image analysis. In: Proceedings of the International Conference on Theory and Application of Diagrams, pp. 330\u2013344 (2000)","DOI":"10.1007\/3-540-44590-0_29"},{"key":"81_CR3","doi-asserted-by":"crossref","unstructured":"Bouaziz, B., Mahdi, W., Hamadou, A.B.: A new video images text localization approach based on a fast Hough transform. In: Proceedings of the International Conference on Image Analysis and Recognition, pp. 414\u2013425 (2006)","DOI":"10.1007\/11867586_39"},{"issue":"6","key":"81_CR4","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J. Canny","year":"1986","unstructured":"Canny J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679\u2013698 (1986)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"81_CR5","doi-asserted-by":"crossref","unstructured":"Carberry, S., Elzer, S., Demir, S.: Information graphics: an untapped resource for digital libraries. In: proceedings of the international conference on research and development in Information Retrieval. pp.581\u2013588 (2006)","DOI":"10.1145\/1148170.1148270"},{"issue":"5","key":"81_CR6","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1109\/72.788646","volume":"10","author":"O. Chapelle","year":"1999","unstructured":"Chapelle O., Haffner P., Vapnik V.N.: Support vector machines for histogram-based image classification. IEEE Trans. Neural Netw. 10(5), 1055\u20131064 (1999)","journal-title":"IEEE Trans. Neural Netw."},{"key":"81_CR7","doi-asserted-by":"crossref","unstructured":"Datta, R., Li, J., Wang, J.Z.: Content-based image retrieval\u2014approaches and trends of the new age. In: Proceedings of the 7th International Workshop on Multimedia Information Retrieval, Singapore, November 2005, pp.253\u2013262 (2005)","DOI":"10.1145\/1101826.1101866"},{"key":"81_CR8","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/361237.361242","volume":"15","author":"R.O. Duda","year":"1972","unstructured":"Duda R.O., Hart P.E.: Use of the Hough transform to detect lines and curves in pictures. Commun. ACM 15, 11\u201315 (1972)","journal-title":"Commun. ACM"},{"issue":"6","key":"81_CR9","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1109\/34.9112","volume":"10","author":"L.A. Fletcher","year":"1988","unstructured":"Fletcher L.A., Kasturi R.: A robust algorithm for text string separation from mixed text\/graphics images. IEEE Trans. Pattern Anal. Mach. Intell. 10(6), 910\u2013918 (1988)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"81_CR10","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1145\/356625.356627","volume":"6","author":"H. Freeman","year":"1974","unstructured":"Freeman H.: Computer processing of line-drawing images. ACM Comput. Surv. 6(1), 57\u201397 (1974)","journal-title":"ACM Comput. Surv."},{"key":"81_CR11","volume-title":"Summarization of diagrams in documents. Advances in automated text summarization","author":"R.P. Futrelle","year":"1999","unstructured":"Futrelle R.P.: Summarization of diagrams in documents. Advances in automated text summarization. MIT Press, Cambridge (1999)"},{"key":"81_CR12","doi-asserted-by":"crossref","unstructured":"Giles, C.L., Bollacker, K., Lawrence, S.: CiteSeer: An automated citation indexing system. In: Proceedings of the ACM Conference on Digital Libraries, pp. 89\u201398 (1998)","DOI":"10.1145\/276675.276685"},{"issue":"2","key":"81_CR13","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0734-189X(90)90030-Y","volume":"51","author":"L. O\u2019Gorman","year":"1990","unstructured":"O\u2019Gorman L.: k \u00d7\u00a0 k thinning. Comput. Vis. Graph. Image Process. 51(2), 195\u2013215 (1990)","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"81_CR14","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"3","author":"R.M. Haralick","year":"1973","unstructured":"Haralick R.M., Dinstein I., Shanmugam K.: Textural features for image classification. IEEE Trans. Syst. Man Cybernet. 3, 610\u2013621 (1973)","journal-title":"IEEE Trans. Syst. Man Cybernet."},{"issue":"12","key":"81_CR15","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1109\/34.643893","volume":"19","author":"M. Heath","year":"1997","unstructured":"Heath M., Sarkar S., Sanocki T., Bowyer K.: A robust visual method assessing the relative performance of edge-detection algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 19(12), 1338\u20131359 (1997)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"81_CR16","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/34.481543","volume":"18","author":"A.K. Jain","year":"1996","unstructured":"Jain A.K., Karu K.: Learning texture discrimination masks. IEEE Trans. Pattern Anal. Mach. Intell. 18(2), 195\u2013205 (1996)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"81_CR17","unstructured":"Jeong, K.Y., Jung, K., Kim, E.Y., Kim, H.J.: Neural network-based text location for news video indexing. In: International Conference on Image Processing, pp.319\u2013323 (1999)"},{"key":"81_CR18","volume-title":"Making Large-Scale Support Vector Machine Learning Practical","author":"T. Joachims","year":"1998","unstructured":"Joachims T.: Making Large-Scale Support Vector Machine Learning Practical. MIT Press, Cambridge (1998)"},{"issue":"5","key":"81_CR19","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 K.I., Jain A.K.: Text information extraction in images and videos: a survey. Pattern Recognit. 37(5), 977\u2013997 (2004)","journal-title":"Pattern Recognit."},{"issue":"1","key":"81_CR20","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1142\/S0218001495000043","volume":"9","author":"C.M. Lee","year":"1995","unstructured":"Lee C.M., Kankanhalli A.: Automatic extraction of characters in complex scene images. Int. J. Pattern Recognit. Artif. Intell. 9(1), 67\u201382 (1995)","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"issue":"9","key":"81_CR21","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1109\/83.862641","volume":"9","author":"J. Li","year":"2000","unstructured":"Li J., Gray R.M.: Context-based multiscale classification of document images using wavelet coefficient distributions. IEEE Trans. Image Process. 9(9), 1604\u20131616 (2000)","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"81_CR22","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1109\/78.823977","volume":"48","author":"J. Li","year":"2000","unstructured":"Li J., Najmi A., Gray R.M.: Image classification by a two-dimensional hidden Markov model. IEEE Trans. Signal Process. 48(2), 517\u2013533 (2000)","journal-title":"IEEE Trans. Signal Process."},{"key":"81_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, J.Z.: Real-time computerized annotation of pictures. In: Proceedings of the ACM international conference on Multimedia, pp. 911\u2013920, Santa Barbara (2006)","DOI":"10.1145\/1180639.1180841"},{"issue":"1","key":"81_CR24","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/83.817607","volume":"9","author":"H. Li","year":"2000","unstructured":"Li H., Doerman D., Kia O.: Automatic text detection and tracking in digital video. IEEE Trans. Image Process. 9(1), 147\u2013156 (2000)","journal-title":"IEEE Trans. Image Process."},{"key":"81_CR25","unstructured":"Liu, Y., Lu, H., Xue, X., Tan, Y.P.: Effective video text detection using line features. In: Proceedings of the International Conference on Control, Automation, Robotics, and Vision, pp. 1528\u20131532 (2004)"},{"key":"81_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Q., Jung, C., Kim, S., Moon, Y., Kim, J.: Stroke filter for text localization in video images. In: Proceedings of the International Conference on Image Processing, pp. 1473\u20131476 (2006)","DOI":"10.1109\/ICIP.2006.312560"},{"key":"81_CR27","unstructured":"Mao, W., Chung, F., Lanm, K., Siu, W.: Hybrid Chinese\/English text detection in images and video frames. In: Proceedings of International Conference on Pattern Recognition, pp. 31015\u201331018 (2002)"},{"key":"81_CR28","doi-asserted-by":"crossref","unstructured":"Maree, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 34\u201340, June (2005)","DOI":"10.1109\/CVPR.2005.287"},{"issue":"2","key":"81_CR29","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/34.273729","volume":"16","author":"J. Ohya","year":"1994","unstructured":"Ohya J., Shio A., Akamatsu S.: Recognizing characters in scene images. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 214\u2013224 (1994)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"81_CR30","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/34.3898","volume":"10","author":"A. Okazaki","year":"1988","unstructured":"Okazaki A., Kondo T., Mori K., Tsunekawa S., Kawamoto E.: An automatic circuit diagram reader with loop-structure-based symbol recognition. IEEE Trans. Pattern Anal. Mach. Intell. 10(3), 331\u2013341 (1988)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"81_CR31","doi-asserted-by":"crossref","unstructured":"Pan, W., Bui, T., Suen, S.: Text segmentation from complex background using sparse representations. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 412\u2013416 (2007)","DOI":"10.1109\/ICDAR.2007.4378742"},{"key":"81_CR32","volume-title":"Practical Algorithms for Image Analysis","author":"M. Seul","year":"2000","unstructured":"Seul M., O\u2019Gorman L., Sammon M.J.: Practical Algorithms for Image Analysis. Cambridge University Press, Cambridge (2000)"},{"key":"81_CR33","doi-asserted-by":"crossref","unstructured":"Shao, M., Futrelle, R.P.: Recognition and classification of figures in PDF documents. In: Proceedings of the International Workshop on Graphics Recognition, pp. 231\u2013242 (2005)","DOI":"10.1007\/11767978_21"},{"key":"81_CR34","doi-asserted-by":"crossref","unstructured":"Shi, Z., Setlur, S., Govindaraju, V.: Text extraction from gray scale historical document images using adaptive local connectivity map. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 794\u2013798 (2005)","DOI":"10.1109\/ICDAR.2005.229"},{"key":"81_CR35","unstructured":"Sin, B., Kim, S., Cho, B.: Locating characters in scene images using frequency features. In: Proceedings of International Conference on Pattern Recognition, pp. 489\u2013492 (2002)"},{"issue":"12","key":"81_CR36","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"A.W.M. Smeulders","year":"2000","unstructured":"Smeulders A.W.M., Worring M., Santini S., Gupta A., Jain R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349\u20131380 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"81_CR37","doi-asserted-by":"crossref","unstructured":"Song, Y.J., Kim, K.C., Choi, Y.W., Byun, H.R., Kim, S.H., Chi, S.Y., Jang, D.K. Chung, Y.K. : Text region extraction and text segmentation on camera-captured document style images. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 172\u2013176 (2005)","DOI":"10.1109\/ICDAR.2005.234"},{"issue":"2","key":"81_CR38","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1009962928226","volume":"2","author":"R.K. Srihari","year":"2000","unstructured":"Srihari R.K., Zhang Z., Rao A.: Intelligent indexing and semantic retrieval of multimodal documents. Inform. Retr. 2(2), 245\u2013275 (2000)","journal-title":"Inform. Retr."},{"key":"81_CR39","doi-asserted-by":"crossref","unstructured":"Subramanian, K., Natarajan, P., Decerbo, M., Castanon, D.: Character-stroke detection for text-localization and extraction. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 33\u201337 (2007)","DOI":"10.1109\/ICDAR.2007.4378671"},{"key":"81_CR40","doi-asserted-by":"crossref","unstructured":"Szummer, M., Picard, R.W.: Indoor\u2013outdoor image classification. In: International Workshop on Content-Based Access of Image and Video Databases, Bombay, India, pp. 42\u201351 (1998)","DOI":"10.1109\/CAIVD.1998.646032"},{"key":"81_CR41","volume-title":"Introductory Techniques for 3-D Computer Vision","author":"E. Trucco","year":"1998","unstructured":"Trucco E., Verri A.: Introductory Techniques for 3-D Computer Vision. Prentice-Hall, Englewood Cliffs (1998)"},{"issue":"12","key":"81_CR42","doi-asserted-by":"crossref","first-page":"1921","DOI":"10.1016\/S0031-3203(98)00079-X","volume":"31","author":"A. Vailaya","year":"1998","unstructured":"Vailaya A., Jain A., Zhang H.: On image classification: \u201ccity images vs. landscapes\u201d. Pattern Recognit. 31(12), 1921\u20131935 (1998)","journal-title":"Pattern Recognit."},{"key":"81_CR43","volume-title":"Wavelets and Subband Coding","author":"M. Vetterli","year":"1995","unstructured":"Vetterli M., Kovacevic J.: Wavelets and Subband Coding. Prentice-Hall, Englewood Cliffs (1995)"},{"key":"81_CR44","doi-asserted-by":"crossref","unstructured":"Yang, C., Dong, M., Fotouhi, F.: Region based image annotation through multiple-instance learning. In: Proceedings of the ACM international conference on Multimedia, pp. 435\u2013438, Singapore (2005)","DOI":"10.1145\/1101149.1101245"},{"issue":"8","key":"81_CR45","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1109\/34.608290","volume":"19","author":"Y. Yu","year":"1997","unstructured":"Yu Y., Samal A., Seth S.C.: A system for recognizing a large class of engineering drawings. IEEE Trans. Pattern Anal. Mach. Intell. 19(8), 868\u2013890 (1997)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"81_CR46","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/ICDAR.1995.598963","volume":"1","author":"Y. Zhong","year":"1995","unstructured":"Zhong Y., Karu K., Jain A.K.: Locating text in complex color images. Int. Conf. Doc. Anal. Recognit. 1, 146\u2013149 (1995)","journal-title":"Int. Conf. Doc. Anal. Recognit."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-009-0081-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-009-0081-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-009-0081-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T23:47:43Z","timestamp":1739058463000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-009-0081-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,4,16]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,7]]}},"alternative-id":["81"],"URL":"https:\/\/doi.org\/10.1007\/s10032-009-0081-0","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,4,16]]}}}