首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于小波能量加权的医学图像融合新算法
引用本文:何凯,何明一,吴晓荣,高涛.基于小波能量加权的医学图像融合新算法[J].科学技术与工程,2006,6(13):1949-1954.
作者姓名:何凯  何明一  吴晓荣  高涛
作者单位:陕西省信息获取与处理重点实验室,西北工业大学电子信息学院,西安,710072
摘    要:目前的大多数基于小波变换的医学图像融合算法,由于没有细致考虑低频分量融合规则以及高频分量邻域特征对于融合效果的重要性,因而得到的融合效果有时并不理想.现提出一种小波域按邻域加窗能量加权的融合准则,该准则根据人体颅部18F-FDG和MRI-T1图像的特点,充分考虑到了低频分量和高频分量邻域特征,对原图像高、低频小波系数分别选用具有不同物理意义的窗矩阵进行邻域加窗能量计算,以归一化加窗能量为权值对各小波系数进行加权,得到融合小波系数,经过小波反变换重构出融合图像.实验证明,采用提出的融合算法得到的融合图像很好地包含了源图像的信息,该算法在医学图像融合应用中比传统的小波系数取大算法、加权平均算法及按邻域方差加权算法效果更好.

关 键 词:医学图像融合  18F-FDG  MRI-T1  小波变换  高、低频窗函数  LHLE算法
文章编号:1671-1815(2006)13-1949-06
收稿时间:2006-01-13
修稿时间:2006年1月13日

A New Medical Image Fusion Method Based on Energy Weighting Algorithm in Wavelet Domain
HE Kai,HE Mingyi,WU Xiaorong,GAO Tao.A New Medical Image Fusion Method Based on Energy Weighting Algorithm in Wavelet Domain[J].Science Technology and Engineering,2006,6(13):1949-1954.
Authors:HE Kai  HE Mingyi  WU Xiaorong  GAO Tao
Abstract:Most of current algorithms of image fusion are based on wavelet transform and the importance of the fusion algorithm in approximation coefficients and the information of neighbor region in detail coefficients are not sufficiently taken into account, thus failing to get perfect fusion effect in some circumstances. A new wavelet image fusion algorithm based on the analysis of the neighbor region energy of the wavelet coefficients is proposed. This algorithm fully considers the approximation coefficients fusion algorithm, the information of neighbor region in detail coeffcients and the characteristics of FDG and MRI images. By employing different masks, the algorithm integrates the approximation coefficients and the detail coefficients differently according to the weights, which are the energy of the corresponding neighbor region of the wavelet coefficients. Reconstructed from the integrated coefficients, the image contains almost all useful information of the original images. Evaluations of the experiment results according to both the subjective and objective criteria demonstrats that the proposed algorithm is more effective than the traditional algorithms.
Keywords:medical image fusion 18F-FDG MRI-T1 wavelet transform high-low frequency mask LHLE algorithm
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
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