Skip to Main content Skip to Navigation
Journal articles

Analyse d'Images de Documents Anciens: une Approche Texture

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00355243
Contributor : Nicholas Journet <>
Submitted on : Thursday, January 22, 2009 - 2:20:21 PM
Last modification on : Monday, May 4, 2020 - 4:42:02 PM
Document(s) archivé(s) le : Tuesday, June 8, 2010 - 9:06:30 PM

File

TS-08.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00355243, version 1

Citation

Nicholas Journet, Rémy Mullot, Veronique Eglin, Jean-Yves Ramel. Analyse d'Images de Documents Anciens: une Approche Texture. Traitement du Signal, Lavoisier, 2008, 24 (6), pp.461-479. ⟨hal-00355243⟩

Share

Metrics

Record views

638

Files downloads

1303