Abstract
In this article, we propose a method of characterization of images of old documents based on a texture approach. This characterization is carried out with the help of a multi-resolution study of the textures contained in the images of the document. Thus, by extracting five features linked to the frequencies and to the orientations in the different areas of a page, it is possible to extract and compare elements of high semantic level without expressing any hypothesis about the physical or logical structure of the analyzed documents. Experimentation based on segmentation, data analysis and document image retrieval tools demonstrate the performance of our propositions and the advances that they represent in terms of characterization of content of a deeply heterogeneous corpus.
Similar content being viewed by others
References
Allier, B., Emptoz, H.: Font type extraction and character prototyping using gabor filters. ICDAR 02, 799–804 (2003). http://doi.ieeecomputersociety.org/
Antonacopoulos A.: Page segmentation using the description of the background. Comput. Vis. Image Underst. 70(3), 350–369 (1998). doi:10.1006/cviu.1998.0691
Basa P., Sabari P.S., Nishikanta R.: Gabor filters for document analysis in Indian bilingual documents. Proc. Int. Conf. Intell. Sens. Inf. Process. 1, 123–126 (2004)
Bres, S.: Contributions a la quantification des critFres de transparence et d’anisotropie par une approche globale. Ph.D. thesis, LIRIS, Université de Lyon (1994)
Caron Y., Charpentier H., Makris P., Vincent N.: Power law dependencies to detect regions of interest. Lect. Notes Comput. Sci. 2886, 495–503 (2003)
Chan W., Coghill G.: Text analysis using local energy. Pattern Recognit. 34(12), 2523–2532 (2001)
Chetverikov, D., Liang, J., Komuves, J., Haralick, R.M.: Zone classification using texture features. In: ICPR ’96, vol. III–7276, p. 676. IEEE Computer Society, Washington, DC (1996)
Cinque L., Lombardi L., Manzini G.: A multiresolution approach for page segmentation. Pattern Recogn. Lett. 19(2), 217–225 (1998). doi:10.1016/S0167-8655(97)00169-4
Doermann, D.: The indexing and retrieval of document images: a survey. Comput. Vis. Image Underst. CVIU 70(3), 287–298 (1998). http://citeseer.ist.psu.edu/doermann98indexing.html
Eglin, V.: Contribution a la structuration fonctionnelle des documents imprims. Ph.D. thesis, LIRIS (1998)
Eglin V., Bres S.: Analysis and interpretation of visual saliency for document functional labeling. Int. J. Doc. Anal. Recognit. 7(1), 28–43 (2004). doi:10.1007/s10032-004-0127-2
Etemad K., Doermann D., Chellappa R.: Multiscale segmentation of unstructured document pages using soft decision integration. IEEE Trans. Pattern Anal. Mach. Intell. 19(1), 92–96 (1997). doi:10.1109/34.566817
Hall-Beyer, M.: Glcm texture: a tutorial. Technical report (2000). http://www.cas.sc.edu/geog/rslab/Rscc/mod6/6-5/texture/tutorial.html, GLCM
Haralick R., Shanmugam K., Dinstein I.: Textural features for image classification. SMC 3(6), 610–621 (1973)
Journet, N., Mullot, R., Ramel, J.Y., Eglin, V.: Ancient printed documents indexation: a new approach. In: ICAPR (1), pp. 580–589 (2005)
Kaufman L., Rousseeuw P.J.: Finding Groups in Data. Wiley, New York (1990)
Khedekar, S., Ramanaprasad, V., Setlur, S., Govindaraju, V.: Text–image separation in devanagari documents. In: ICDAR ’03: Proceedings of the Seventh International Conference on Document Analysis and Recognition, vol. 2, p. 1265. IEEE Computer Society, Washington, DC (2003)
Laws, K.I.: Rapid texture identification. In: Image processing for missile guidance; Proceedings of the Seminar, San Diego, CA, July 29–August 1, 1980 (A81-39326 18-04) Bellingham, WA, Society of Photo-Optical Instrumentation Engineers, pp. 376–380 (1980)
Ma, H., Doermann, D.: Gabor filter based multi-class classifier for scanned document images. In: ICDAR ’03: Proceedings of the Seventh International Conference on Document Analysis and Recognition, p. 968. IEEE Computer Society, Washington, DC (2003)
Maderlechner G., Suda P., Breckner T.: Classification of documents by form and content. Pattern Recogn. Lett. 18(11–13), 1225–1231 (1997). doi:10.1016/S0167-8655(97)00098-6
Mao S., Rosenfeld A., Kanungo T.: Document structure analysis algorithms: a literature survey. SPIE 5010, 197–207 (2003)
Marinai, S., Marino, E., Soda, G.: Tree clustering for layout-based document image retrieval. In: Proceedings of DIAL ’06, pp. 243–253. IEEE Computer Society, Washington, DC (2006). doi:10.1109/DIAL.2006.44
Nagy, G., Kanai, J., Krishnamoorthy, M., Thomas, M., Viswanathan, M.: Two complementary techniques for digitized document analysis. In: DOCPROCS ’88: Proceedings of the ACM Conference on Document Processing Systems, pp. 169–176. ACM Press, New York (1988). doi:10.1145/62506.62539
Nicolas S., Kessentini Y., Paquet T., Heutte L.: Handwritten document segmentation using hidden Markov random fields. ICDAR 1, 212–216 (2006)
Pavlidis T., Zhou J.: Page segmentation by white streams. ICDAR 2, 945–953 (1991)
Ramel J., Busson S., Demonet M.: Agora: the interactive document image analysis tool of the bvh project. DIAL 0, 145–155 (2006). doi:10.1109/DIAL.2006.2
Shafait F., Keysers D., Breuel T.M.: Performance comparison of six algorithms for page segmentation. In: Procedings of the Seventh IAPR Workshop on Document Analysis Systems (DAS) 3872, 368–379 (2006)
Shi Z., Govindaraju V.: Multi-scale techniques for document page segmentation. ICDAR 0, 1020–1024 (2005). doi:10.1109/ICDAR.2005.165
Tuceryan, M.: Moment-based texture segmentation. PRL 15(7), 659–668 (1994). http://citeseer.ist.psu.edu/tuceryan94moment.html
Uttama, S., Ogier, J., Loonis, P.: Top-down segmentation of ancient graphical drop caps. GREC, pp. 87–95 (2005)
Wong K.Y., Casey R.G., Wahl F.M.: Document analysis system. IBM J. Res. Dev. 26(6), 647–656 (1982)
Youness G., Saporta G.: Une méthodologie pour la comparaison de partitions. Revue de Statistique Appliquée 52, 97–120 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Journet, N., Ramel, JY., Mullot, R. et al. Document image characterization using a multiresolution analysis of the texture: application to old documents. IJDAR 11, 9–18 (2008). https://doi.org/10.1007/s10032-008-0064-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-008-0064-6