Segmentation Technique for Acute Leukemia Blood Cells Images using Saturation Component and Moving K-Mean Clustering Procedures *Nor Hazlyna Harun,*Mohd Yusof Mashor, # Rosline Hassan *Electronic & Biomedical Intelligent Systems (EBItS) Research Group, School of Mechatronic Engineering, Universiti Malaysia Perlis, 02600 Jejawi, Arau, Perlis, MALAYSIA # Hematology Department, University Hospital, University Science Malaysia, Kubang Kerian, Kelantan, MALAYSIA e-mail:hazlyna_harun@yahoo.com ABSTRACT Image segmentation is the most important step and critical task in image processing as it will directly affect the post-processing. One of the common segmentation techniques is using clustering algorithm. Clustering technique is commonly used as a digital image segmentation including medical images. The current study proposes an automated color image segmentation using combination of saturation component of HSI color space, a Moving K- means clustering and 7x7 pixels median filter. In the proposed technique, saturation formula was applied to ease the segmentation process. After that, Moving K-means clustering was used to segment the blasts from acute leukemia blood images automatically. After the segmentation process has been completed, 7x7 pixels median filter was applied to eliminate and remove unwanted noise. To measure the efficiency of the proposed technique, pixel subtraction technique will be used. The results show that the proposed technique has successfully segmented and distinguished most of the acute leukemia blood cells from its background, while preserving significant features compared to the method based on a conventional K- means clustering algorithm.