Multilevel Thresholding as a Simple Segmentation Technique in Acute Leukemia Images

Generally, image processing technique involved five basic components which are image acquisition, image pre-processing, image segmentation, post-processing and image analysis. The most critical step in analysis of image and image processing is segmentation of the object of interest in an image. Basically, segmentation of the image divides the whole image into some unique disjoint regions. This paper represents an approach of image segmentation on microscopic bone marrow images by using multilevel thresholding technique. This technique has been applied into two types of images which are normal bone marrow and Acute Lymphoblastic Leukemia (ALL). A multilevel thresholding is proposed as a method in segmenting of white blood cells (WBCs) from its complicated background. The segmentation technique in an image should retain maximum useful information and discard unwanted information makes the whole process critical. This segmentation technique expected to be one of segmentation technique that could possibly to differentiate well between normal bone marrow and ALL in further analysis.