Texture Feature Based Image Retrieval

With the Multimedia information widely used, and the promotion of the research of database system and computer vision, content-based image retrieval (CBIR) is becoming a hot research area. CBIR is different from traditional text-based image retrieval. In fact, CBIR is a system which can realize organizing and retrieving images automatically and intelligently through extracting some features from images and finding the most similar images which have the most similar feature with the indexed image.In the CBIR system, feature extracting and matching is the key point of deciding the result of the system. We compared several feature extracting methods which are color features, texture features, and shape features. Since texture feature can describe the properties of smooth, sparse, and order of images, this paper decide to do image retrieval based on texture features. On the other hand, this paper uses relevance feedback to change values of different features to improve the index rate.We proposed a new texture feature extracting method based on two traditional methods. Gabor filters are good at extracting information in frequency and direction from local area of images and co-occurrence matrixes are good at extracting important information from the whole images. So we unite both of these two methods to extract texture features of images and used the method successfully into CBIR system..