基于特征点的伪匹配点去除算法

Removing False Matching Points Algorithm Based on Feature Points

基于特征点的图像配准中伪匹配点的存在影响变换矩阵的计算精度,容易造成图像配准失败.根据SIFT特征匹配中存在的伪匹配点,提出一种伪匹配点去除算法.两幅待配准图像的正确匹配点在坐标位置上有差值相似性,伪匹配点的坐标差值与正确匹配点的坐标差值差异大,利用这种坐标差值的波动对伪匹配点进行去除.实验结果表明,待配准图像中的伪匹配点得到了有效去除,与RANSAC算法相比,时间复杂度大幅减小.

Accuracy of transformation matrix is usually affected by false matching points. More seriously, this status can cause failure of image registration. In order to remove false matching points , this paper proposes a algorithm based on the existence of false matching points in SIFT feature matching. True matching points of two registration images to be matched is similar in coordinate differ- ence,and the coordinate difference of error matching points is different from the coordinate difference of true matching points. According to this discipline, false matching points can be removed by the difference between coordinate difference. Finally, the proposed algorithm is illustrated by different images. Experiment results show that error matching points in registration image axe effectively removed and the complexity of time is significantly reduced comparing with RANSAC algorithm.