一种新的基于图像矩的特征匹配算法

A Novel Feature Matching Algorithm Based on Image Moment

基于图像矩理论,提出一种新的图像特征匹配算法.该算法在原有经典的Scale-Invariant FeatureTransform(SIFT)图像匹配算法的基础上,利用图像一阶矩确定特征点指定大小的圆形邻域的质心,并通过利用质心来确定特征点主方向的方式提高匹配算法的效率.通过对图像矩特征的有效利用,与SIFT算法相比,此算法在保持较好的图像特征点匹配性能的同时,显著降低了算法的时间复杂度,具有更好的实时性能.计算机实验证明了此算法的有效性.

This paper proposes a novel image feature matching algorithm based on the image moment theory.The algorithm makes use of the intensity centroid of the circle neighborhood of the keypoint which is defined by the first order moment of the image to determine the main orientation of the keypoint to improve the efficiency of the algorithm.Through the effective use of the characteristic of image moment,compared with the SIFT algorithm,the proposed algorithm achieves a good matching performance of the image feature points,and significantly reduces the computational complexity of the algorithm simultaneously,thus having a better real-time performance.The computer experiments shows the effectiveness of the algorithm