Image retrieval using global descriptors and multiple clustering in Nash game

Abstract

In order to improve the retrieval accuracy of content-based image retrieval systems, we consider the Content-based image retrieval formulated as a Nash game. In the present approach by splitting the optimization variables into three players. The first player minimizes its objective function by using the first strategy (Color descriptor), the second player acts by using the second strategy (Gist descriptor), and the third one by using the third strategy (SIFT descriptor). We will use the Nash equilibrium to detect the classes of membership of the searched image.