Automatic Central Object Extraction from Color Image

With the development of content-based multimedia systems, there is a need for automatic extraction of central object from natural color images. A new method for automatic extraction of central object is presented in this paper. First, a criterion of homogeneity based on both the global and the local information for HSV color images is proposed, and is used to get the "E-image". The high and low values of the E-image correspond to possible region boundaries and region interiors respectively. Then, a method to determine the candidate object seed points set and the candidate background seed points set in the image is given. Finally, the candidate object seed region growing and merging are used to extract the central object from the image. Experimental results demonstrate the effectiveness of the method for the natural color images.