Abstract
One of the big hurdles facing current content-based image retrieval (CBIR) is the semantic gap between the low-level visual features and the high-level semantic features. We proposed an approach to describe and extract the global texture semantic features. According to Tamura texture model, we utilize the linguistic variable to describe the texture semantics, so it becomes possible to depict the image in linguistic expression such as coarse, fine. And we use genetic programming to simulate the human visual perception and extract the semantic features value. Our experiments show that the semantic features have good accordance with the human perception, and also have good retrieval performance. In some extent, our approach bridges the semantic gap in CBIR.