Document image characterization using a multiresolution analysis of the texture: application to old documents |
| |
Authors: | Nicholas Journet Jean-Yves Ramel Rémy Mullot Véronique Eglin |
| |
Affiliation: | (1) Department of Biotechnology, IIT-Madras, Chennai, 600036, India; |
| |
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. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|