SUMMARY This paper proposes a method for classifying leukemia. Leukemia is divided into 2 categories which are acute leukemia and chronic leukemia and other subordinate types. Our work focuses on classification of Foil of Bretagne (Lymphoid) and Almeida Lloyd (Myeloid). The experiment results showed that the performance of identification leukemia using our image processing techniques could classify Lymphoid stem cells and Myeloid stem cells. The features are extracted from the segmented images and classified using the Support Vector Machine (SVM). The method has been evaluated using a set of 100 images with 50 abnormal samples and 50 normal samples obtained. The computer simulations show that the proposed system robustly segments and classifies blood images. Features extracted from the segmented cytoplasm and nucleus, are motivated by the visual cues of shape and texture. The MIC classification proposed six subtypes of ALL and 10 subtypes of AML that are characterized by unique morphologic, immunologic, and cytogenetic features Immunologic (MIC group) markers CD34 stem cell. We have obtained an accuracy of 91.29 %.