Comparative analysis of segmentation algorithms using threshold and K-mean clustering

Abstract

Worldwide many parasitic diseases infect human being and cause deaths due to misdiagnosis. These parasites infect Red Blood Cells (RBCs) from blood stream. Diagnosis of these diseases is carried out by observing thick and thin blood smears under the microscope. In this paper segmentation of blood cells from microscopic blood images using K-Mean clustering and Otsu’s threshold is compared. Segmentation is important innovation for identification of parasitic diseases. Number of blood cells is an essential count. Preprocessing is carried out for noise reduction and enhancement of blood cells. Preprocessing is fusion of background removal and contrast stretch techniques. Preprocessed image is given for segmentation. In segmentation separation of overlapping blood cells is done by watershed transform. Segmentation using K-Mean clustering is more suitable for segmentation of microscopic blood images.