Image segmentation based on maximum relationship principle of conditional distribution under the assumption of Poisson distribution

Image segmentation is one of the most difficult and important steps in image analysis. Segmentation accuracy determines the eventual success or failure of computerized analysis procedures. The thresholding method is considered as one widely used method in image segmentation. It is considered by Kittle and Illingworth that the optimum threshold of segmentation can be calculated by the method of probability statistics, if the mixture density function composed of object and background is known and estimated. Suppose that the gray histogram of image obeys Poisson distribution, a new method of segmentation based on the maximum relationship principle of conditional distribution is proposed in this paper. The new method is compared with Ostu method and the minimum error method, the result shows that the proposed one is good and the performance is stable.