Mapping Image Low-Level Descriptors to Semantic Concepts

Our goal is to organize the image contents semantically. In this paper, we propose a method to classify the images semantically, using the C-fuzzy algorithm to segment the natural scenes into perceptually uniform regions. The low-level characteristics that are taken into account are: color, texture, shape, absolute spatial arrangement, spatial coherency, and dimension. Since humans are the ultimate users of most image retrieval systems, it is important to organize the contents semantically, according to meaningful categories. This requires an understanding of the important semantic categories that humans use for image classification, and the extraction of meaningful image features that can discriminate between these categories. A lot of experiments, in which the human subjects had to group images into semantic categories and to explain the criteria for their choice, were realized. From these experiments, we identify the semantic categories (landscapes, animals, flowers, etc), the semantic indicators or intermediate descriptors and their visual characteristics.