A Novel Content-Based Image Retrieval Approach Using Fuzzy Combination of Color and Texture

A novel content-based image retrieval approach using fuzzy combination of color and texture image features is expressed in this paper. To accomplish this, color histogram and autocorrelogram of the partitioned image as color features and Gabor wavelet as texture feature are used. Color and texture features are separately extracted and kept as feature vectors. In comparing images similarity stage, the difference between feature vectors is computed. Since center of image is more important, higher weight is considered for it in the comparison of autocorrelograms, and due to this fact the retrieval performance is improved; and also finding the most similar regions using autocorrelogram of the other regions, makes the algorithm more invariant to rotation and to somehow to changing the viewing angle. To make the final decision about images similarity ratio, a fuzzy rule-based system is utilized. Experimental results show this method improved the performance of content-based image retrieval systems.