The Study of Reduce the Mismatch Based on the SIFT Feature Matching
The algorithm of SIFT (scale-invariant feature transform) feature matching is an international hotspot in the areas of the keypoints matching and target recognition at the present time.The algorithm is used in the image matching widely because of the good invariance of scale,illumination and space rotation.This paper proposes a new theory to reduce the mismatch—the theory to reduce the mismatch based on the main orientation ofkeypoints.This theory should firstly compute the grads of the main orientation of a couple of matched keypoints in the two images and the difference between them.Because the difference of the main orientation of matched keypoints should be much larger than the couples which are matched correctly,we can distinguish and reduce the mismatch through setting the proper threshold,and it can improve the accuracy of the SIFT algorithm greatly.
SIFT algorithm invariance of scale the match of images reduce the mismatch
Liu Xiaoyu Piao Yan Liu Lei
College of Electronic Information Engineering, Changchun University of Sdence and Technology, Changchun130022, China
国际会议
太原
英文
378-382
2012-08-17（万方平台首次上网日期，不代表论文的发表时间）