基于SVM的图像分割E.pdf

Medical image segmentation based on threshold SVM Chen Xiao-juan Li Dan Information Engineering College Information Engineering College NorthEast Dianli University(NEDU) NorthEast Dianli University(NEDU) JiLin ，JiLin，China JiLin ，JiLin，China cxj_neiep@126.com lidan0401@ Abstract—Medical image segmentation is a basic problem in with threshold method at the beginning to get training sample medical image processing field and the key to the problem from set and then precisely and automatically with SVM.The processing to analyzing.Medical image segmentation based on experiment shows that the new method is feasible and its SVM needs the category attribute of image training sample set in performance is nice,in which the lung is segmented from the order to achieve the goal of image segmentation by machine chest X-ray film. learning.The method of obtaining sample set manually involves heavy workload,what is worse,the accuracy entirely depends on II. ALGORITHM the experience of operators.Therefore this paper proposes a second-order segmentation method based on threshold SVM.The experiment shows that the new method is feasible and its A. Threshold Segmentation Algo