Old Document Image Analysis: a Texture Approach. Analyse d’Images de Documents Anciens: une Approche Texture

Old Document Image Analysis: a Texture Approach

Analyse d’Images de Documents Anciens: une Approche Texture

Nicholas Journet Jean-Yves Ramel  Véronique Eglin  Rémy Mullot 

Laboratoire d’Informatique, 64 avenue Jean Portalis, 37200 Tours

LIRIS-UMR 5205, INSA de Lyon, Bâtiment Jules Verne, 69621 Villeurbanne cedex

L3I, Université de La Rochelle, Pôle Sciences et Technologie, 17042 La Rochelle cedex

Page: 
461-479
|
Received: 
29 January 2007
|
Accepted: 
N/A
|
Published: 
31 December 2007
| Citation

OPEN ACCESS

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 analysed documents.Experimentations demonstrate the performance of our propositions and the advances that they represent in terms of characterization of content of a deeply heterogeneous corpus.

Résumé

Dans cet article,nous proposons une méthode de caractérisation d’images d’ouvrages anciens basée sur une approche texture. Cette caractérisation est réalisée à l’aide d’une étude multirésolution des textures contenues dans les images de documents. Ainsi,en extrayant cinq indices liés aux fréquences et aux orientations dans les différentes parties d’une page,il est possible d’extraire et de comparer des éléments de haut niveau sémantique sans émettre d’hypothèses sur la structure physique ou logique des documents analysés. Des expérimentations montrent la faisabilité de la réalisation d’outils d’aide à la navigation ou d’aide à l’indexation. Au travers de ces expérimentations,nous mettrons en avant la pertinence de ces indices et les avancées qu’ils représentent en terme de caractérisation de contenu d’un corpus fortement hétérogène.

Keywords: 

Document image analysis,Texture features,Multiresolution,digital libraries,indexation.

Mots clés

Analyse d’images de documents,indices texture,multirésolution,indexation,bibliothèque numérique.

1. Introduction
2. Les Méthodes de Caractérisation de Contenu d’Images de Documents
3. Notre Approche Texture pour la Caractérisation du Contenu
4. Vers de Nouvelles Applications de Recherche d’Information par le Contenu
5. Conclusion et Perspectives
  References

[All04] B. ALLIER. Contribution à la Numérisation des Collections : Apports des Contours Actifs. PhD thesis, LIRIS, université de Lyon, 2004. 

[Ant98] Apostolos ANTONACOPOULOS. Page segmentation using the description of the background. Comput. Vis. Image Underst., 70(3):350-369, 1998. 

[BC97] Andrea BOZZI and Sylvie CALABRETTO. The digital library and computational philology: The bambi project. In ECDL '97: Proceedings of the First European Conference on Research and Advanced Technology for Digital Libraries, pages 269-285, London, UK, 1997. Springer-Verlag. 

[BELM00] BOUCHÉ, EMPTOZ, LEBOURGEOIS, and METZGER. Debora projet européen. Technical report, LIRIS, université de Lyon, 2000. 

[Bre94] BRES. Contributions à la quantification des critères de transparence et d'anisotropie par une approche globale. PhD thesis, LIRIS, université de Lyon, 1994. 

[Bre02] Thomas M. BREUEL. Two geometric algorithms for layout analysis. In DAS '02: Proceedings of the 5th International Workshop on Document Analysis Systems V, pages 188-199, London, UK, 2002. Springer-Verlag. 

[BSN04] BASA, SABARI, and NISHIKANTA. Gabor filters for document analysis in indian bilingual documents. Proceedings International Conference on Intelligent Sensing and Information Processing, pages 123-126, 2004. 

[CC01] W. CHAN and G. COGHILL. Text analysis using local energy. Pattern Recognition, 34(12):2523-2532, December 2001. 

[CCMV03] Yves CARON, Harold CHARPENTIER, Pascal MAKRIS, and Nicole VINCENT. Power law dependencies to detect regions of interest. Lecture Notes in Computer Science, 2886/2003:495-503, November 2003. 

[CLKH96] D. CHETVERIKOV, J. LIANG, J. KOMUVES, and R. M. HARALICK. Zone classification using texture features. In ICPR '96: Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276, page 676, Washington, DC, USA, 1996. IEEE Computer Society. 

[CLM98] L. CINQUE, L. LOMBARDI, and G. MANZINI. A multiresolution approach for page segmentation. Pattern Recogn. Lett., 19(2):217-225, 1998. 

[CR03] COUASNON and RAPP. Accès par le contenu aux documents manuscrits d'archives numérisées. Document numérique, 7:61-84, 2003. 

[CWS03] Zheru CHI, Qing WANG, and Wan-Chi SIU. Hierarchical content classification and script determination for automatic document image processing. Pattern Recognition, 36(11):2483-2500, 2003. 

[Doe98] David DOERMANN. The indexing and retrieval of document images: a survey. Comput. Vis. Image Underst., 70(3):287-298, 1998. 

[EDC97] Kamran ETEMAD, David DOERMANN, and Rama CHELLAPPA. Multiscale segmentation of unstructured document pages using soft decision integration. IEEE Trans. Pattern Anal. Mach. Intell., 19(1):92-96, 1997. 

[Egl98] V. EGLIN. Contribution à la structuration fonctionnelle des documents imprimés. PhD thesis, LIRIS, 1998. 

[HB00] Mryka HALL-BEYER. Glcm texture: A tutorial. Technical report, 2000. 

[HI03] Karim HADJAR and Rolf INGOLD. Arabic newspaper page segmentation. icdar, 02:895-900, 2003. 

[HOP+95] David HARWOOD, Timo OJALA, Matti PIETIK, Shalom KELMAN, and Larry DAVIS. Texture classification by center-symmetric auto-correlation, using kullback discrimination of distributions. Pattern Recogn. Lett., 16(1):1-10, 1995. 

[HSD73] R.M. HARALICK, K. SHANMUGAM, and I. DINSTEIN. Textural features for image classification. SMC, 3(6):610-621, November 1973. 

[Jou06] N. JOURNET. Analyse d'images de documents anciens : une approche texture. PhD thesis, {L3I}, université de La Rochelle, 2006. 

[KIM99] K. KISE, M. IWATA, and K. MATSUMOTO. On the application of voronoi diagrams to page segmentation. Proc. of the Workshop on Document Layout Interpretation and Its Applications, (IV-C):1-4, September 1999. 

[KRSG03] Swapnil KHEDEKAR, Vemulapati RAMANAPRASAD, Srirangaraj SETLUR, and Venugopal GOVINDARAJU. Text - image separation in devanagari documents. In ICDAR '03: Proceedings of the Seventh International Conference on Document Analysis and Recognition, volume 2, page 1265, Washington, DC, USA, 2003. IEEE Computer Society. 

[Law80] K. I. LAWS. 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, 1980, p. 376-380., pages 376-380, 1980. 

[LG00] J. LI and R.M. GRAY. Context-based multiscale classification of document images using wavelet coefficient distributions. 9(9):16041616, September 2000. 

[Lou00] Etienne LOUPIAS. Indexation d'images : aide au télé-enseignement et similarités pré-attentives. PhD thesis, LIRIS, 2000. 

[LWT04] Yue LU, Zhe WANG, and Chew Lim TAN. Word grouping in document images based on voronoi tessellation. Lecture Notes in Computer Science, 3163:147 - 157, 2004. 

[MD05] H. MA and D. S. DOERMANN. Font identification using the grating cell texture operator. 5676:148-156, 2005. 

[MM96a] W. Y. MA and B. S. MANJUNATH. Texture features and learning similarity. CVPR, 00:425, 1996. 

[MM96b] B. S. MANJUNATH and W. Y. MA. Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell., 18(8):837-842, 1996. 

[MMS06] Simone MARINAI, Emanuele MARINO, and Giovanni SODA. Tree clustering for layout-based document image retrieval. In DIAL '06: Proceedings of the Second International Conference on Document Image Analysis for Libraries (DIAL'06), pages 243-253, Washington, DC, USA, 2006. IEEE Computer Society. 

[MRK03] MAO, ROSENFELD, and KANUNGO. Document structure analysis algorithms:A literature survey. SPIE, 5010:197-207, 2003. 

[NKK+88] George NAGY, Junichi KANAI, Mukkai KRISHNAMOORTHY, Mathews THOMAS, and Mahesh VISWANATHAN. Two complementary techniques for digitized document analysis. In DOCPROCS '88: Proceedings of the ACM conference on Document processing systems, pages 169-176, New York, NY, USA, 1988. ACM Press. 

[NKPH06] NICOLAS, KESSENTINI, PAQUET, and HEUTTE. Handwritten document segmentation using hidden markov random fields. ICDAR, 1:212-216,August 2006. 

[O'G93] L. O'GORMAN. The document spectrum for page layout analysis. PAMI, 15(11):1162-1173, November 1993. 

[OP00] OKUN and PIETIKÄINEN. A survey of texture-based methods for document layout analysis. Texture Analysis in Machine Vision, 40:165-177, 2000. 

[PA02] CORNU Philippe and SMOLARZ André. Caractérisation d'images par textures associées. Traitement du signal (Trait. signal), 19(1):2935, 2002. 

[Pra78] W.K. PRATT. Digital Image Processing (Book : First Edition). Wiley, 1978. 

[PVU+06] Rudolf PARETI, Nicole VINCENT, Surapong UTTAMA, JeanMarc OGIER, Jean-Pierre SALMON, Salvatore TABBONE, Laurent WENDLING, and Sebastien ADAM. On defining signatures for the retrieval and the classification of graphical drop caps. dial,0:220-231, 2006. 

[PZ91] PAVLIDIS and ZHOU. Page segmentation by white streams. ICDAR, 2:945-953, 1991. 

[RBD06] J.Y. RAMEL, S. BUSSON, and M.L. DEMONET. Agora: the interactive document image analysis tool of the bvh project. DIAL, 0:145-155, 2006. 

[Ros99] C. ROSENBERG. Mise en oeuvre d'un système adaptatif de segmentation d'images. PhD thesis, Laboratoire d'analyse des systèmes de traitement de l'information, ENSSAT, 1999. 

[RPR05] S.S. RAJU, P.B. PATI, and A.G. RAMAKRISHNAN. Text localization and extraction from complex color images. ISVC05, pages 486-493, 2005. 

[SG05] Zhixin SHI and Venu GOVINDARAJU. Multi-scale techniques for document page segmentation. ICDAR, 0:1020-1024, 2005. 

[SKB06] Faisal SHAFAIT, Daniel KEYSERS, and Thomas M. BREUEL. Performance comparison of six algorithms for page segmentation. 3872:368-379, Feb 2006. 

[TJ98] M. TUCERYAN and A. K. JAIN. Texture analysis. In The Handbook of Pattern Recognition and Computer Vision (2nd Edition), pages 207-248, 1998. 

[Tru05] TRUPIN. La reconnaissance d'images de documents: Un panorama.  Traitement du Signal, 22(3):159-1892, 2005. 

[Tuc94] M. TUCERYAN. Moment-based texture segmentation. PRL, 15(7):659-668, July 1994. 

[TZ00] Chew Lim TANand Zheng ZHANG. Text block segmentation using pyramid structure. Document Recognition and Retrieval VIII, 4307(1):297-306, 2000. 

[UOL05] UTTAMA, J. OGIER, and P. LOONIS. Top-down segmentation of ancient graphical drop caps. GREC, pages 87-95, 2005. 

[WCW82] WONG, CASEY, and WAHL. Document analysis system, ibm journal of research and development. IBM Journal of Research and Development, 26:647-656, 1982. 

[YS04] YOUNESSand SAPORTA. Une méthodologie pour la comparaison de partitions. Revue de Statistique Appliquée, 52:97-120, 2004.