Abstract
In this paper, we present a new method for printed text characterization. This method is based on a text visibility and legibility criterion. The text is analyzed through its typographic form. So, we propose to label different kinds of text according to their visual aspect and their textural contents (especially their size, their density but also the line and letter spacing). A scale of legibility and of structural relief of forms has realized this discrimination. The texture is characterized with a statistical analysis of density, which is impervious (insensitive) to our multiscale approach. This statistical analysis is at the basis of the text labeling. This work is a part of a complete scheme of physical and logical document segmentation. It is dedicated to the classification of texts according to their eye-catching properties.
Chapter PDF
References
Akindele, Belaid, A labeling approach for mixed Document Blocks, Proceedings of ICDAR 93, 2nd International Conference on Document Analysis and Recognition, Japan, pp.749–752, 1993.
J.C. Anigbogu, Reconnaissance de textes imprimés mulitfontes à l'aide de modéles stochastiques. Thèse de doctorat: Université de Nancy, 1992.
C. Bonnet and B. Dresp. Psychophysique de l'extraction des contours en vision humaine, RF IA 3,102–109, 1991.
E. Charlaix, D. Derrien-Peden, Reconnaissance de la structure logique de documents par programmation par contraintes sur les styles,CNED'96, pp.61–68, 1996.
V. Eglin, Structuration de documents par une modélisation floue de l'information visuelle. Logique Floue et Application, LFA'97, 10p., 1997.
A.K. Jain, K. Bhattacharjee, Test segmentation' using Gabor filters for automatic document processing, MVA'92, pp. 169–184, 1992.
B. Julesz, Preconscious and Conscious Processes in Vision. Bell Laboratories. Murray Hill, New Jersey. Pattern Recognition Mechanisms, pp. 333–359, 1985.
J.C. Lecas, L'attention visuelle, Liège: Pierre Mardaga, 1992, 310p.
J. Ninio, L'empreinte des sens, Perception, mémoire, langage. Odile Jabob, 310p., 1991.
F. Richeaudeau, Manuel de typographie et de mise en page, 1989.
J. Wey-Wen, H.E. Meadows, Classification and compression on digital newspaper images, VCIP, pp.96–105, 1993.
A. Zramdini, R.Ingold, Optical font recognition from projection profiles. Third International Conference on Raster Imaging and Digital Typography, Darmstadt, Allemagne, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eglin, V., Bres, S., Emptoz, H. (1998). Characterization and classification of printed text in a multiscale context. In: Amin, A., Dori, D., Pudil, P., Freeman, H. (eds) Advances in Pattern Recognition. SSPR /SPR 1998. Lecture Notes in Computer Science, vol 1451. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0033325
Download citation
DOI: https://doi.org/10.1007/BFb0033325
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64858-1
Online ISBN: 978-3-540-68526-5
eBook Packages: Springer Book Archive
