A spatial constrained K-means approach to image segmentation

General purposed color image segmentation is a challenging and important issue in image processing related applications. However, few systems successfully handle this issue for a broad diversity of images. In this paper, we are seeking a practical and generic solution to image segmentation. As a fast segmentation process, K-means based clustering is employed in feature space first. Then, in image plane, the spatial constraints are adopted into the hierarchical K-means clusters on each level. The two processes are carried out alternatively and iteratively. Also, an effective region merging method is proposed to handle the over segmentation. Extensive experiments show the proposed approach is fast and generic, thus practical in applications.