| 一种基于小波变换的配准特征点自动标记算法 |
| |
| 引用本文： | 周平,李传富,陈荻,周康源. 一种基于小波变换的配准特征点自动标记算法[J]. 北京生物医学工程, 2007, 26(4): 356-359 |
| |
| 作者姓名： | 周平 李传富 陈荻 周康源 |
| |
| 作者单位： | 中国科学技术大学电子工程与信息科学系,合肥,230027;安徽中医学院第一附属医院影像中心,合肥,230031 |
| |
| 基金项目： | 安徽省教委自然科学基金重点研究项目 |
| |
| 摘 要： | 以颅脑CT图像为研究对象,提出了一种基于小波变换的自动标记非刚性配准所需对应特征点的算法.这种算法充分考虑了颅脑CT图像的像素点及其临域的纹理特征,通过进行小波变换建立对应于每个像素点的多分辨率小波特征向量,并以小波特征向量间的差异作为判别依据,在目标图像中标记非刚性配准所需的对应特征点.一系列的实验结果表明,这种基于小波变换的算法能够准确地在目标图像中标记出配准所需的对应特征点,可以作为基于特征的非刚性配准对应特征点自动标记的参量之一.
|
| 关 键 词： | CT图像 纹理特征 小波特征向量 多分辨率 |
| 文章编号： | 1002-3208（2007）04-0356-04 |
| 收稿时间： | 2006-04-17 |
| 修稿时间： | 2006-04-172006-05-30 |
An algorithm of automatic correspondence detection for deformable registration based on wavelet transform |
| |
| ZHOU Ping,LI Chuanfu,CHEN Di,ZHOU Kangyuan. An algorithm of automatic correspondence detection for deformable registration based on wavelet transform[J]. Beijing Biomedical Engineering, 2007, 26(4): 356-359 |
| |
| Authors: | ZHOU Ping LI Chuanfu CHEN Di ZHOU Kangyuan |
| |
| Affiliation: | 1. Department of EEIS, University of Science and Technology of China, Hefei 230027;2 Medical Imaging Center,First Affiliated Hospital of Anhui TCM College,Hefei 230031 |
| |
| Abstract: | A algorithm of automatic correspondence detection in brain CT image based on wavelet transform is presented.Adequately the algorithm thinks about the grain feature of pixel and its neighborhood in brain CT image,subsequently constructs a multi-resolution wavelet-based attribute vector(WAV) of the pixel.The WAV's difference is used to detect the correspondence pixel in object image.Experimental results show the algorithm based on wavelet transform can detect correspondence accurately in object image,it would be one of parameters of automatic correspondence detection for deformable registration based on features. |
| |
| Keywords: | CT image grain feature wavelet-based attribute vector multi-resolution |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
