首页 | 本学科首页   官方微博 | 高级检索  
     

基于主成份分析和支持向量机的MRI图像多目标分割
引用本文:郭磊,武优西,刘雪娜,颜威利,沈雪勤. 基于主成份分析和支持向量机的MRI图像多目标分割[J]. 中国生物医学工程学报, 2007, 26(4): 498-502,516
作者姓名:郭磊  武优西  刘雪娜  颜威利  沈雪勤
作者单位:1. 河北工业大学电气与自动化学院,天津,300130
2. 河北工业大学计算机科学与软件学院,天津,300130
基金项目:河北省自然科学基金;教育部高等学校博士学科点专项科研基金
摘    要:在MRI图像中,颅内各组织的边界极其复杂且不规则,这对传统的分割算法提出严峻的挑战.主成份分析(PCA)可达到降维和消除冗余信息的目的,为使支持向量机(SVM)准备的样本空间更为紧凑、合理.本研究采用PCA将图像的57维特征向量处理后,研究多分类SVM对MRI图像进行多目标分割,成功提取颅内各组织不规则边界.理论和实验表明,基于PCA和SVM相结合的分割性能优于仅采用SVM的分割性能.

关 键 词:主成份分析  支持向量机  图像分割
文章编号:0258-8021(2007)04-0498-05
修稿时间:2006-10-262007-06-04

The Segmentation of Multi-target MRI Image Based on Principal Component Analysis and Support Vector Machine
GUO Lei,WU You-Xi,LIU Xue-Na,YAN Wei-Li,SHEN Xue-Qin. The Segmentation of Multi-target MRI Image Based on Principal Component Analysis and Support Vector Machine[J]. Chinese Journal of Biomedical Engineering, 2007, 26(4): 498-502,516
Authors:GUO Lei  WU You-Xi  LIU Xue-Na  YAN Wei-Li  SHEN Xue-Qin
Affiliation:1 School of Electrical and Automation, Hebei University of Technology, Tianjin 300130; 2 School of Computer Science and Software, Hebei University of Technology, Tianjin 300130
Abstract:In MRI image,the boundary of each encephalic tissue is very complicated and irregular.It is a big challenge to the traditional segmentation algorithms.Principal Component Analysis(PCA) can realize dimension reduction and eliminate redundant information,make the sample space for Support Vector Machine(SVM) more compact and reasonable.In this paper,PCA was used to process 57 dimensional feature vectors of image and the segmentation of multi-target MRI image based on multi-classification SVM was investigated.The result showed that the irregular boundary of each encephalic tissue was extracted successfully.The theory analysis and experimental results indicated that the segmentation based on PCA and SVM displayed better performance than the segmentation based on SVM only.
Keywords:principal component analysis    support vector machine    image segmentation
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号