Color image segmentation by seeded region growing and region merging

Based on HSV color model, a method of color image segmentation by automatic seed selection and region growing is proposed. The non-edge and smoothness at pixel's neighbor are used as criterion to determine automatically which ones are seed pixels. The seed pixels are merged to form seed region if they are connected. A seeded region growing method is used to segment the image based on seed regions. Region merging is used to merge similar regions or small regions. The new method is applied to segment many natural color images, and experimental results show the effectiveness and efficiency of the method.

I. Introduction

Image segmentation often serves as a crucial initial step before performing high-level tasks such as object recognition and content-based image retrieval ^[1]–[2]. It should be noted that there is no single standard approach to segmentation. Selection of an appropriate segmentation technique depends on the type of images and applications. The existing image segmentation techniques can be classified into the following approaches, thresholding techniques, boundary-based techniques, region-based techniques, clustering-based techniques and hybrid techniques ^[3]–[8].