A dynamical system approach to texel identification in regular textures

We propose a texture analysis method based on Rényi’s entropies. The method aims at identifying texels in regular textures by searching for the smallest window through which the minimum number of different visual patterns is observed when moving the window over a given texture. The experimental results show that any of Rényi’s entropies can be used for texel identification. However, the second order entropy, due to its robust estimation, is the most reliable. The main advantages of the proposed method are its robustness and its flexibility. We illustrate the usefulness and the effectiveness of the method in a texture synthesis application and we compare it with other structural approaches.