Segmentation Using Fuzzy Clustering

Cell segmentation is one of important steps in the automatic white blood cell differential counting. In this paper, we propose a technique to segment single-cell images of white blood cells in bone marrow into two regions, i.e., nucleus and non-nucleus. The seg-mentation is based on the fuzzy C-means clustering and mathematical morphology. The segmentation results are compared to an expert’s manually seg-mented images. The initial investigation of the use of the derived segmented images in the cell classifica-tion is also performed by using the Bayes classifier