Color Image Proling Using Fuzzy Sets
Amine Aït Younes, Isis Truck, Plaine Saint-Denis, Herman Akdag · 2005
In this article, a software for image indexing and retrieval is presented. The classication proposed here is based on the dominant color(s) of the images. The process consists in assigning a colorimetric prole to the image in HLS space (Hue, Lightness, Saturation). First, the denition of hue is done thanks to a fuzzy representation to take into account the non-uniformity of colors distribution. And then, lightness and saturation are represented through linguistic qualiers also dened in a fuzzy way. Finally, the prole is built through fuzzy functions representing the membership degree of the image to dierent classes. In order to improve the performances i.e. to dene more accurate proles, we propose to consider zones of pixels, instead of pixels individually. Those zones can be constructed thanks to an edge detection algorithm. A sample of pixels is chosen inside a zone to determine the color of the zone. According to the detected dominant colors, such a software may be used to classify indoor/outdoor images for example, or harmonious/disharmonious images :::