Semantic rules classification for images annotation

In this paper, we present an approach to facilitate the annotation and the retrieval of the image documents. Our approach is based on the definition and the generation of semantic rules presented via the logic of predicates. Then, we proposed the classification of these rules by a method of clustering Fuzzy C-means. For this, we used the method of co-citation to calculate the similarity measure between images. This classification has grouped thematically these images with the aim to facilitate research and annotation. To validate our proposal, we implemented a tool tested on a set of images of the city center. Finally, we conducted a series of tests to evaluate our approach.