A novel content based image retrieval method based on splitting the image into homogeneous regions

Color histograms are widely used for content-based image retrieval. Their advantages are efficiency and insensitivity to small changes in camera viewpoint. However, this technique does not employ spatial information of image colors. To take spatial information into account, some local color feature-based approaches proposed. However, these approaches have some disadvantages such as low effectiveness, consuming computation times and storage. This paper proposes a novel technique for retrieving images called HR (Homogeneous Region), which is based on splitting images into two homogeneous regions. We carry out an experiment on an image database containing 10,000 images. Experimental results show that our technique is more effective than the color coherence vector (CCV) and Color Based Clustering based retrieval techniques.