Color-Oriented Content Based Image Retrieval

The aim of this work is to study a metrics that represents the perceptive space of the colors. Besides we want to furnish innovative methods and tools for annotate and seek images. The experimental results have shown that in tasks of evaluation of the similarity, the subjects don’t refer to the most general category of “color”, but they create subordinate categories in base to some particular color. Those categories contain all the variations of this color and also they form intersections between categories in which any variations are shared. The perception of the variations is not isometric; on the contrary that perception is weighed in different manner if the variations belong to a particular color. So the variations that belong to the intersection area will have different values of similarity in relation to the own category. We developed a system of color-oriented content-based image retrieval using this metrics. This system analyzes the image through features of color correspondents to the own perception of the human being. Beyond to guarantee a good degree of satisfaction for the user, this approach furnishes a novelty in the development of the CBIR systems. In fact there is the introduction of a criterion to index the figures; it is very synthetic and fast.