A Fast Algorithm for Segmentation of Microscopic Cell Images

In this paper we introduce a fast algorithm for the segmentation of breast nuclei in the microscopic images of fine needle aspiration. The algorithm depends on the color information of the nuclei to separate them from the background. It consists of two main steps. First, apply Sobel edge detection method on the blue component of the image to separate touching nuclei. Second, the green component of the image is thresholded to separate the nuclei from the background. The algorithm correctly segmented 80% of the nuclei and it is also fast compared to previous algorithms.