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.

No abstract

No abstract

Character recognition has a continuous importance for several years and recently, new challenges appeared with camera-based pictures. This paper deals with text extraction for color natural scenes images. Many papers try to combine several color spaces or to choose the best one for a particular database. We show that the main problem is not in the choice of color spaces for generic text extraction but in the choice of clustering distances to handle all degradations present in this kind of images. Comparative results are given using a public database.

Abstract