| 结合SURF特征和RANSAC算法的图像配准方法 |
| |
| 引用本文： | 纪利娥,陈磊.结合SURF特征和RANSAC算法的图像配准方法[J].传感器世界,2013,19(10):6-7. |
| |
| 作者姓名： | 纪利娥 陈磊 |
| |
| 作者单位： | 中北大学信息与通信工程学院,山西太原,030051;中北大学信息与通信工程学院,山西太原,030051 |
| |
| 摘 要： | 提出了一种基于SURF特征和RANSAC算法的图像配准方法。首先通过SURF算法对图像进行特征点检测，将欧式距离作为相似性测度进行特征点粗匹配，并通过RANSAC算法剔除误匹配点对；然后利用正确的匹配点对求解仿射变换模型从而实现图像的精确配准。实验结果表明了该方法的精确性和有效性。
|
| 关 键 词： | 图像配准 SURF特征 RANSAC算法 特征点匹配 |
An image registration method based on SURF features and RANSAC algorithm |
| |
| Jl Li-e,CHEN-Lei.An image registration method based on SURF features and RANSAC algorithm[J].Sensor World,2013,19(10):6-7. |
| |
| Authors: | Jl Li-e CHEN-Lei |
| |
| Affiliation: | Information and Communication Engineering College, North University of China, Taiyuan 030051 ,China |
| |
| Abstract: | An image registration method based on SURF feature and RANSAC algorithm is proposed. Firstly, SURF algorithm is used to detect the image feature points. The Euclidean distance is taken as similarity measure to complete coarse matching of feature points, and the RANSAC algorithm is applied to remove false matching points. Then, the affine transformation model is solved according to the correct matching points and the images are registered accurately. The experiment results show that the proposed method has good performance of accuracy and efficiency. |
| |
| Keywords: | image registration SURF feature RANSAC algorithm featurematching |
| 本文献已被 维普 万方数据 等数据库收录！ |
