Indexing and Retrieval Scheme of the Image Database based on Color and Spatial Relations

We propose a new approach to retrieve images from an image MTM (Mathematical Transform to Munsell) for filtering out the non-similar images effectively. Then, we combine the color and spatial relationship of objects to measure the similarity of images. . . database. We combine both color and spatial features of a picture to index and measure the similarity of images. We propose a new automatic indexing scheme of image database according to our clustering method, which could firter the image e#ciently. As a technical contribution, a Seed-Filling like algorithm that could extract the shape and spatial relationship feature of image is proposed. Also, the system is incorporated with a visual intetface, which allows the user to spectjj objects as the spatial specifcation of pictures. With color identification and spatial similarity functions, the preliminary experience shows that the system is able to retrieve image information of a very high satisfaction.