Leukemia Image Segmentation using K-Means Clustering and HSI Color Image Segmentation

During the unfolding measures that are taken for the purpose of leukemia detection, segmentation of blood cells is a vital step. In this paper two approaches of such segmentation technique is proposed. While one uses K-means clustering, other uses color image based segmentation method. Both the processes segment the image into two regions, blasts & backgrounds. These blasts are our area of interest. The performance measure is based on the comparison of the two proposed techniques tends to find the more suitable approach for correct leukemia image segmentation. The results show that the segmentation based on K-means clustering gives better results preserving important information and removing background noise.