A New Approach for Segmentation and Identification of Disease Affected Blood Cells

The analysis of blood cells in microscope image can provide useful information concerning the health of the patient. To analyze, identify and diagnose - digital image processing techniques is much more effective than manual observation. The major intension of this paper is to detect the nucleus and cytoplasm of blood cells. The proposed work is useful to detect different kind of disease like anemia, leukemia etc on the basis of the condition of nucleus. This will also helpful for hematologists for clear identification and counting of blood cells. Finally the proposed work designed to obtain effective and more accurate result than other conventional edge detection techniques like Canny, Sobel, and Laplacian of a Gaussian. The result indicates 85% accuracy for identification of different type of cells as well as nucleus.