White blood cell (WBC) segmentation, which is important for cytometry, is a challenging issue because of the morphological diversity of WBCs and the complex and uncertain background of blood smear images. This paper proposes a novel method for the nucleus and cytoplasm segmentation of WBCs for cytometry. A color adjustment step was also introduced before segmentation. Color space decomposition and k-means clustering were combined for segmentation. A database including 300 microscopic blood smear images were used to evaluate the performance of our method. The proposed segmentation method achieves 95.7% and 91.3% overall accuracy for nucleus segmentation and cytoplasm segmentation, respectively. Experimental results demonstrate that the proposed method can segment WBCs effectively with high accuracy.
This paper presents a novel method for segmentation of white blood cells (WBCs) in peripheral blood and bone marrow images under different lights through mean shift clustering, color space conversion and nucleus mark watershed operation (NMWO). The proposed method focuses on obtaining seed points. First, color space transformation and image enhancement techniques are used to obtain nucleus groups as inside seeds. Second, mean shift clustering, selection of the C channel component in the CMYK model, and illumination intensity adjustment are employed to acquire WBCs as outside seeds. Third, the seeds and NMWO are employed to precisely determine WBCs and solve the cell adhesion problem. Morphological operations are further used to improve segmentation accuracy. Experimental results demonstrate that the algorithm exhibits higher segmentation accuracy and robustness compared with traditional methods.