Abstract
This paper presents an approach for content-based image retrieval of both texture and non-texture images. With the growth of the number of images in digital format, modern image retrieval systems employ content-based image retrieval. Our system uses automated segmentation technique followed with region based feature extraction. The system employs clustering of images to speed up the retrieval process. The proposed system achieved an accuracy of 97.56%. The result demonstrate that the searching of an image is fast and accurate.