The invention relates to a colonic polyp image segmentation method based on a cellular automaton model for mainly solving the problems of low segmentation efficiency, poor repeatability and low segmentation precision in the existing colonic polyp image segmentation technology. The technical scheme of the invention is as follows: (1) reading a coloscope color image containing polyp; (2) restoring a highlight area in the image; (3) primarily detecting a polyp area in the image; (4) marking a seed pixel; (5) constructing the cellular automaton model; (6) initializing the cellular automaton model; (7) performing image segmentation; and (8) outputting a segmented image. According to the colonic polyp image segmentation method provided by the invention, by means of the priori knowledge that the shape of the polyp is close to an ellipse, the seed pixel is automatically marked, the cellular automaton model is constructed, the image segmentation is performed by a formulated local conversion rule, the local information of the image is fully used, the colonic polyp image segmentation method has the advantage of high segmentation efficiency and high accuracy, and can be applied to the automatic segmentation of colonic polyp images.