Automatic Color Image Segmentation Using a Square Elemental Region-Based Seeded Region Growing and Merging Method

Abstract: This paper presents an efficient automatic color image segmentation method using a seeded region growing and merging method based on square elemental regions. Our segmentation method consists of the three steps: generating seed regions, merging the regions, and applying a pixel-wise boundary determination algorithm to the resultant polygonal regions. The major features of our method are as follows: the use of square elemental regions instead of pixels as the processing unit, a seed generation method based on enhanced gradient values, a seed region growing method exploiting local gradient values, a region merging method using a similarity measure including a homogeneity distance based on Tsallis entropy, and a termination condition of region merging using an estimated desired number of regions. Using square regions as the processing unit substantially reduces the time complexity of the algorithm and makes the performance stable. The experimental results show that our method exhibits stable performance for a variety of natural images, including heavily textured areas, and produces good segmentation results using the same parameter values. The results of our method are fairly comparable to, and in some respects better than, those of existing algorithms.