An unsupervised GVF snake approach for white blood cell segmentation based on nucleus

Segmentation accuracy, as the first step in an image analysis system, impacts on whole system efficiency. In normal human blood microscopic image, which contains white and red blood cells, because of high accumulation of red cells, there exist touch and overlap between these cells. They are two difficult issues in image segmentation which common segmentation algorithms cannot overcome them. We have employed GVF snake to segment white cells which are clinically more important than red cells. In spite of traditional snakes, in GVF snakes it is not necessary to localize initial snake near the desired boundaries. On the other hand, nucleus which is laid inside white cell is the darkest part of image which can be localized by an adaptive histogram analysis. In this paper, we have proposed to use the convex hull of the boundary of nucleus as initial contour to detect white cell and separate it from touching red cells. Thus, initial contour is determined via an unsupervised method. Additionally, edges of nucleus are eliminated from edge map of the image and improve the efficiency of GVF snake a lot. Experimental Results show that our approach is very efficient