Leukocyte nucleus segmentation and recognition in color blood-smear images

In this paper, a leukocyte segmentation and recognition method is proposed for leukocyte differential counting. In general, leukocytes are usually manually classified in laboratories by using microscopes. It is a painstaking and subjective task for biologists. An automatic method is essential to reduce the overhead for biologists. The nuclei are used to identify five types of leukocyte in this paper. The leukocyte cell nucleus enhancer is proposed to segment the region we are interested in by enhancing the region of the leukocyte nucleus and suppressing the other region of the blood smear images. In the recognition steps, we reduce features by principle component analysis (PCA) to obtain suitable features. The genetic algorithm based k-means clustering approach is used to classify the five kinds of leukocyte in the reduced dimensions. The experimental results show that even though only leukocyte nucleus features are used for classification in our method, we achieve a high and promised accurate recognition rate.