Chuansheng Wang, Hong Zhang*, Zuoyong Li*, Xiaogen Zhou*, Yong Cheng and Rongyan Chen Pages 1 - 9 ( 9 )
White blood cell (WBC) image segmentation plays a key role for cell morphology analysis. However, WBC segmentation is still a challenging task due to the diversity of WBCs. In this paper, we present a novel WBC segmentation method based on color component combination and contour fitting. Specifically, the proposed method first uses color component combination and image thresholding to achieve nuclear segmentation, then uses a color prior to remove image background and extract the initial WBC contour via edge detection, and finally judges and closes the unclosed WBC contour by contour fitting. Accordingly, cytoplasmic segmentation can be achieved by subtracting the nuclear region from the WBC region. Experimental results on 140 WBC images under two staining conditions showed that the proposed method improved segmentation accuracy and robustness.
white blood cell (WBC) segmentation, color component combination, color prior, image background removal, Canny edge detection, contour fitting
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou, College of Mathematics and Computer Science, Fuzhou University, Fuzhou, P.R. China; e School of Communication Engineering, Nanjing Institute of Technology, Nanjing, School of Communication Engineering Nanjing Institute of Technology, Department of Clinical Laboratory, the People's Hospital Affiliated to Fujian University of Traditional Chinese Medicine, Fuzhou