Overlapping Cell Separation Research

Clinical tests which included blood smears, urine sediment, pathology and other sections of the cell samples inspection,in early, were completed by the artificial. And the result of artificial detection is low efficiency, strong professionalism and so on. So we need use computer that can autoaticly identify cell images which can effectively avoid these question, and it becomes a hot at home and abroad..In the process of automatic identification cell images, Cell Segmentation is one of the most important steps. Segmentation results have a direct relation to the following of cell images identification. Because of the diversity and complexity of the cell images, at present,there is no method can correctly separate all the cell images. No matter select which segmentation algorithm, it will always have overlapping cells in the cell images. So finding a new segmentation algorithm which can resolve the problem is emergent. It is a special division that we seprate overlapping and adhesion particle to single particle. This paper is to resolve this problem.At frist, this paper introduce current status of home and abroad, and segmentation algorithms which based on regional segmentation, segmentation edge detection and specific theory segmentation. The paper compared and analyzed these segmentations and pointed out the advantages and disadvantages. The algorithms of separating overlapping cell are mainly based on mathematical morphology. On the base of comparing and analyzing these segmentations and pointing out the advantages and disadvantages,an algorithm based on improved math morphology separating is presented in the paper for the problem. Using a simple and fast contour separating computation the algorithm can obtain transformed distance .Then, we use the watershed method to separate cells. Experimental results show that the algorithm has a good separation effects.Finally, this paper summarizes all the works and views the future work that will separate long and narrow cells and irregular single cells.