| 基于多尺度小波变换角点特性的图像配准研究 |
| |
| 引用本文： | 张瑞华,吴谨.基于多尺度小波变换角点特性的图像配准研究[J].天津师范大学学报(自然科学版),2011,31(4):44-49. |
| |
| 作者姓名： | 张瑞华 吴谨 |
| |
| 作者单位： | 1. 武汉科技大学信息科学与工程学院,武汉430081;中国人民解放军空军雷达学院实验中心,武汉430019
2. 武汉科技大学信息科学与工程学院,武汉,430081 |
| |
| 基金项目： | 国家自然科学基金资助项目 |
| |
| 摘 要： | 针对传统单尺度角点检测算法易产生伪角点和在角点匹配过程中计算复杂,容易产生误匹配等缺点,提出一种基于多尺度小波变换角点特性的图像配准方法.该算法首先采用多尺度小波变换的二维图像角点检测算法采检测参考图和待配准图的角点信息,然后采用两图角点对的欧几里德距离平均值的极小值作为两图角点对配准准则,利用改进的粒子群优化(Par...
|
| 关 键 词： | 图像配准 小波变换 角点检测 改进的PSO算法 |
Image registration based on multi-scale wavelet transform corners with sub-pixel localization |
| |
| ZHANG Ruihua,WU Jin.Image registration based on multi-scale wavelet transform corners with sub-pixel localization[J].Journal of Tianjin Normal University(Natural Science Edition),2011,31(4):44-49. |
| |
| Authors: | ZHANG Ruihua WU Jin |
| |
| Institution: | ZHANG Ruihua1,2,WU Jin1(1.School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China,2.Experiment Center,Air Force Radar Academy,Wuhan 430019,China) |
| |
| Abstract: | To deal with the faults of traditional single-scale corner detection including false and unstable corners,high computational complexity and incorrect matching,a new image registration algorithm is proposed based on improved corner feature.Firstly,a multi-scale wavelet-based corners algorithm is used to detect the corners in reference image and temp image.And then a simple local random search(LRS) procedure is adopted to search local optimal solutions.Lastly,translation parameters are calculated by using imp... |
| |
| Keywords: | image registration wavelet transform corner detection particle swarm optimization(PSO) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
