White blood cell segmentation for fresh blood smear images

White blood cell diagnosis is usually performed by doctors manually through visual examination of blood smears under microscope. It is a time consuming, tedious, and susceptible to error, so an automatic process using computerized system is preferable. In this automatic process, segmentation and classification of white blood cell are the most important stages. An automatic segmentation technique for microscopic white blood cell images focusing on images from fresh blood smears is proposed in this paper. The segmentation is conducted using a proposed method that consists of an integration of several digital image processing algorithms. Sixty microscopic blood images were tested, and the proposed method obtained 92% accuracy for cytoplasm segmentation and 89% accuracy for nucleus segmentation.