基于特征点对齐度的图像配准方法
doi: 10.3724/SP.J.1146.2005.00901
A New Method for Image Registration Based on Alignment Metric of Feature Points
-
摘要: 该文提出了一个新的匹配准则特征点对齐度准则，并在此基础上提出了一种基于特征点对齐度准则的图像配准方法。首先，利用小波多尺度积提取出图像的特征点及其角度信息，再利用该文提出的特征点对齐度准则计算所有特征点对之间的对齐度，从而得到匹配点对。实验结果证明了该方法的精确性和有效性。
-
关键词:
- 对齐度;多尺度积;小波
Abstract: A new matching metricalignment metric of feature points is defined, and a new approach to image registration based on alignment metric of feature points is proposed. Feature points and their angles are detected by using wavelet multi-scale product, then the alignment metric of all feature points are calculated, so matching points can be obtained. The experimental results illustrate the algorithm has a good performance of accuracy and efficiency. -
[1] Brown L G. A survey of image registration techniques[J].ACM Computing Surveys.1992, 24(4):325-376 [2] Zitova B and Flusser J. Image registration methods: A survey[J].Image and Vision Computing.2003, 21(11):977-1000 [3] 谌安军，陈炜，毛士艺. 一种基于边缘的图像配准方法. 电子 与信息学报，2004, 26(5): 679-684. Zhan An-jun, Chen Wei, and Mao Shi-yi. An image edge based algorithm for multisensor image registration. Journal of Electronics Information Technology, 2004, 26(5): 679-684. [4] 倪国强，刘琼. 多源图像配准技术分析与展望. 光电工程，2004, 31(9): 1-6. Ni Guo-qiang and Liu Qiong. Analysis and prospect of multi-source image registration techniques. Opto-electronic Engineering, 2004, 31(9): 1-6. [5] 钟家强，王润生. 基于边缘的图像配准改进算法. 计算机工程与科学，2001, 23(6): 25-28. Zhong Jia-qiang and Wang Run-sheng. Image registration using edge-based methods. Computer Engineering and Science, 2001, 23(6): 25-28. [6] Hsieh Jun-Wei. Image registration using a new edge-based approach[J].Computer Vision and Image Understanding.1997, 67(2):112-130 [7] 王东峰，邹谋炎. 基于最大化对齐度的多模态图像自动配准[J].电子与信息学报.2003, 25(6):755-762浏览 [8] 杨丹，张小洪. 基于小波多尺度积的边缘检测算法. 计算机科学，2004, 31(1): 133-135. Yang Dan and Zhang Xiao-hong. Edge detection algorithm based on wavelet multiscale product. Computer Science, 2004, 31(1): 133-135. -
计量
- 文章访问数: 3296
- HTML全文浏览量: 90
- PDF下载量: 1653
- 被引次数: 0
下载:
