AUTOMATIC SEGMENTATION AND IMPACT FOR RETRIEVAL IMAGES

This paper deals about retrieval images based on the content and image segmentation process such as very important step of image analysis and image processing. In present, the image processing and analyzing is still rapidly growing area of research. Image segmentation is the operation that divides image into set of different segments. We present a different type of image segmentation and impact quality of segmentation for retrieval images. Three type of image segmentation was presented. In this case Mean shift, K means and Graph based segmentation. All experiment was done on international database ETHZ Shape classes. The experiments are showed that Graph based segmentation method is good for retrieval simple shapes from real images.