Content Based Image Retrieval using interactive genetic algorithm

Large amounts of databases are created due to the developments in data storage and acquisition technologies. There is a need to develop an appropriate system that will manage these entire databases. Also we need to precisely and effectively retrieve images from these databases for various applications. The Content Based Image Retrieval (CBIR) system serves this purpose. In this paper, we introduce a user based system for CBIR in which genetic algorithm is applied. The different features of color image such as mean, standard deviation and the image bitmap are used for retrieval. In addition, the texture features such as the edge histogram of an image and the entropy of the gray level co-occurrence matrix are used. Furthermore, the genetic algorithm is applied to help the user in identifying the images which satisfy his needs for reducing the gap between the users´ expectation and the retrieval results.