User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

A Rarity-Based Visual Attention Map - Application to Texture Description

Primary tabs

Mancas, Matei [FPMs] Mancas-Thillou, C [FPMs] Gosselin, Bernard [FPMs] Macq, Benoît [UCL]

This paper describes a simple and "pre-cortical" visual attention model, which does not take image directions into account. We compute rarity-based saliency maps and then we describe the relation between texture and visual attention. Finally we decompose the image into several textures with different regularities. Our purpose is to compress textures into images using small repeating patterns

Document type Communication à un colloque (Conference Paper)
Publication date 2006
Language Anglais
Conference "ICIP 2006 (IEEE International Conference on Image Processing)", Atlanta (du 08/10/2006 au 11/10/2006)
Host document IEEE ; "Proceedings of the IEEE International Conference on Image Processing 2006 (ICIP)"- p. 445 - 448 (ISBN : 1-4244-0480-0)
Affiliations FPMs - TCTS
UCL - FSA/ELEC - Département d'électricité
Keywords SIGN
Links
Bibliographic reference Mancas, Matei ; Mancas-Thillou, C ; Gosselin, Bernard ; Macq, Benoît. A Rarity-Based Visual Attention Map - Application to Texture Description .ICIP 2006 (IEEE International Conference on Image Processing) (Atlanta, du 08/10/2006 au 11/10/2006). In: IEEE, Proceedings of the IEEE International Conference on Image Processing 2006 (ICIP), 2006, p. 445 - 448
Permanent URL http://hdl.handle.net/2078.1/90888