Color image segmentation based on seeded region growing with Canny edge detection

A method of color image segmentation by seeded region growing scheme combined with Canny edge detection is proposed. Firstly, we use Otsu method to achieve threshold arguments which make Canny edge detection more effective. Secondly, we input the achieved edge as one of the seed selection conditions to achieve initial seeds. Finally, seeded region growing and region merging take into effect. Experimental results show that the performance of the proposed method is comparable to the popular counterpart.