Acute Myeloid Leukemia (AML) is one of cancer type that attack white blood cells in myeloid descendants. On the clinical examination of leukemia, the number of each blast cell in the laboratory is calculated. However, in some subtype of AML like M4, M5 dan M7 are affected by the same type of precursor cells. The precursor cell of them are myeloblast, monoblast and megakaryoblast, which needs more detailed analysis to distinguish. This research tries to help overcome the problem by doing cell type automatic classification from cells images. Classification is performed on cell types of precursors cells derived from bone marrow preparations. The stages that have been completed are preprocessing, segmentation, extraction and feature selection, and classification. Features used as input of classification stage are area, nucleus ratio, circularity, perimeter, mean, and standard deviation. The results showed the success rate of cell segmentation reached 87.72% of total 1710 cells. The support vector machine classification results in the best performance test data are achieved by Linear kernel. The performance was obtained by combining six features for eight cell types from the maturation of the three precursor cells. These cell types are myeloblast, promyelocyte, granulocyte, monoblast, promonocyte, monocyte, megakaryoblast and support cell with sequential accuracy of 98.67%, 98.01%, 84.05% 99.67%, 95.35%, 89.70%, 99.34% and 98.01% respectively.