基于支持向量机方法的医学图像分割  

Medical image segmentation based on Support Vector Machine approach

作　　者：廖国红[1] 齐军[2] 黄光林 

机构地区：[1]武汉理工大学余家头校区交通学院,武汉430063 [2]武汉数字工程研究所,武汉430074 [3]武汉国测科技有限公司,武汉430223

出　　处：《计算机工程与应用》2007年第29期217-219,共3页Computer Engineering and Applications

基　　金：国家自然科学基金( the National Natural Science Foundation of China under Grant No.60475024)

摘　　要：医学图像分割是图像分割研究领域的难点问题。支持向量机方法被看作是对传统学习分类方法的一个好的替代,特别在小样本、高维情况下,具有较好的泛化性能。论文采用支持向量机方法对医学图像进行分割研究。实验结果表明,支持向量机方法是一种很有前景的医学图像分割技术。Medical image segmentation is a difficult problem in the field of image segmentation.Support Vector Machine approach is considered a good candidate because of its good generalization performance, especially when the number of training samples is very small and the dimension of feature space is very high.This paper investigates the segmentation of medical image based on Support Vector Machine approach.Experimental results show that Support Vector Machine approach is a promising technique for medical image segmentation.

关 键 词：医学图像分割 支持向量机 统计学习理论 泛化性能 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]