COLOR AND TEXTURE FUSION-BASED METHOD FOR CONTENT BASED IMAGE RETRIEVAL

Abstract

Since the last decade, Content-based Image retrieval was a hot topic research. The computational complexity and the retrieval accuracy are the main problems that CBIR system have to avoid. In this study the method was proposed to overcome these problems by using the combine of color moment and texture features. The color feature was extracted by color moment where the images will be in the HSV color space. The textures features extracted by applying Gabor function where the images will be in grayscale. The similarity measure in this study was calculated by used Euclidian distance. The experiments results show that using both color and texture features to describe the image and use them for image retrieval is more accurate than using one of them only.