Hematological malignancies i.e. acute lymphoid leukemia and acute myeloid leukemia are the types of blood cancer that can affect blood, bone marrow, lymphatic system and are the major contributors to cancer deaths. In present work, an attempt has been made to design a CAC (computer aided classification system) for diagnosis of myeloid and lymphoid cells and their FAB (French, American, and British) characterization. The proposed technique improves the AML and ALL diagnostic accuracy by analyzing color, morphological and textural features from the blood image using image processing and to assist in the development of a computer-aided screening of AML and ALL. This paper endeavors at proposing a quantitative microscopic approach toward the discrimination of malignant from normal in stained blood smear. The proposed technique firstly segments the nucleus from the leukocyte cell background and then computes features for each segmented nucleus. A total of 331 geometrical, chromatic and texture features are computed. A genetic algorithm using support vector machine (SVM) classifier is used to optimize the feature space. Based on optimized feature space, an SVM classifier with various kernel functions is used to eradicate noisy objects like overlapped cells, stain fragments, and other kinds of background noises. The significance of the proposed method is tested using 331 features on 420 microscopic blood images acquired from the online repository provided by the American society of hematology. The results confirmed the viability or potential of using a computer aided classification method to reinstate the monotonous and the reader-dependent diagnostic methods.