Research On Image Segmentation Of Cancer Cell

The cancer cell auto-recognition systems are significant in computer assistant diagnosis, especially in the instances of lacking experts. Cell segmentation is the important step in the process of recognition of cancer cell. The segmented result has a great affect on the capability of following recognition and analysis algorithms. However, since images variety and complexity, by now there isn't a segmentation algorithm that fits all kind of images. In this paper, the problem of the image segmentation of overlapping cells is mainly studied. First, traditional pretreatment technologies and segmentation methods are discussed. We can know merit and shortcoming of them. Then the mathematic morphology is produced. The traditional pretreatment technologies and mathematic morphology can eliminate background noise interference effectively together. In segmentation stage, the distance-reconstruction is used, which can improve the traditional watershed algorithm, eliminate the phenomena of over-segmentation.