基于SIFT特征点的图像匹配技术研究

Research of Image Registration Algorithm Based on theSitf Corner Detector

图像配准是遥感、医学、计算机视觉等很多领域中的一个基本问题。针对特征点的匹配，该文首先采用LTS Haus-dorff距离进行特征点的初匹配，然后采用基于Sampson距离的随机抽样一致性算法去除伪匹配的特征点对。实验证明，该方法可以实现图像的精确配准。

Image registration is a fundamental problem in many fields, such as remote sensing, medicine, computer vision and so on. For the registration of feature points, LTS Hausdorff distance to match feature points has been first used, remove false match-ing of feature points with the help of a random sample of consistency. Experiment results show that this method realizes the pre-cise image registration.