Detection of abnormal blood cells on the basis of nucleus shape and counting of WBC

The counting of Red Blood Cells (RBC), White Blood Cells (WBC) and platelet of human blood in microscopic image can provide useful information concerning the health of the patient. The conventional methods used in laboratories to detect and diagnose the problem were very slow and prone to get inaccuracy in result. Digital image processing can detect and recognize different diseases and make it easy to analyze and diagnose the actual problem in a fast and cost effective manner. The major intension of this paper is to count number of WBC and also identify the abnormal ones. The proposed work is useful to detect different kind of diseases like Chronic Obstructive Pulmonary Disease, Immune system disorders, Neutropenia, HIV/AIDS, Lymphocytopenia, leukemia etc on the basis of counts of different blood constituents. This paper is going to provide way to recognize types of different kind of WBC in its normal and abnormal form. 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. The result indicates 85% accuracy for identification and counting of different type of blood cells.