Research On Segmentation Algorithms Of Bone-Marrow Cells Image

With the development of image processing, image processing applications in the medical field are more and more extensive. The segmentation is the key procedures and the basis of segmentation and recognition in digital image field. This paper has a research on segmentation methods of Bone-marrow cells image according to various theories and algorithms.In the image pre-processing, we produces an improved multi-weighted filter algorithm which has a better denoising result with a variety of filtering algorithms. The article introduces the advantages and disadvantages of the edge detection and applies mathematical morphology into cells image segmentation. We use gradient algorithm to enhance cell borders in improving the edge detection algorithm. We achieve a better result through application adaptation threshold algorithm and mathematical morphology.The article introduces Parametric active contour model (Kass model, the balloon model, GVF model), and discuss their advantages and disadvantages. We get the proof that Parametric active contour model is suitable for single cell image segmentation of the Bone-marrow cells image.