Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (13): 199-201.DOI: 10.3778/j.issn.1002-8331.2010.13.060

• 图形、图像、模式识别 • Previous Articles     Next Articles

Medical image fusion algorithm based on 2v-SVM and consistency checking

REN Guo-chao,SHI Li   

  1. School of Electrical Engineering,Zhengzhou University,Zhengzhou 450001,China
  • Received:2008-09-25 Revised:2008-11-21 Online:2010-05-01 Published:2010-05-01
  • Contact: REN Guo-chao

基于2v-SVM和一致性检验的医学图像融合算法

任国超,师 黎   

  1. 郑州大学 电气工程学院,郑州 450001
  • 通讯作者: 任国超

Abstract: Medical image fusion has been the used to derive useful information from multimodality medical image data,so as to provide more information to the doctor and clinical treatment planning system.This paper proposes a fusion rule based on the combination 2v-SVM and consistency checking.The method applies 2v-SVM(Support Vector Machine) to low frequency sub-image,and then for the high frequency sub-image,Consistency checking is adopted.The experiment results demonstrate that the proposed method overcomes the instability and incontinuity of information occurring in the image fusion decomposed by multi-scale before,increase the visual effect and include more information.

Key words: medical image fusion, Wavelet transform, consistency checking, support vector machine

摘要: 对于不同模态的医学图像进行融合处理,可为临床提供更多的诊断信息。提出了一种基于2v-SVM和一致性检验的融合算法,首先对低频子图像采用2v-SVM融合规则;然后在高频部分进行一致性检验。试验结果表明,与传统方法相比,这种方法克服了在图像多尺度分解过程中产生的不稳定性和不连续性的缺点,可以使图像的视觉效果更好,并包含更多的信息。

关键词: 医学图像融合, 小波变换, 一致性检验, 支持向量机

CLC Number: