Image Matching Method Based on Improved SIFT Algorithm
Ruixing Yu · Jisuanji fangzhen · 2011
To improve the resolution of different scales in different image matching accuracy and efficiency,this paper introduces an improved method based on scale invariant feature transform(SIFT) algorithm for image matching.SIFT feature matching algorithm is currently a hot research field,because it has good invariance of scale,rotation,illumination,based on analyzing the generating process of SIFT feature vectors,the quasi-Euclidean distance instead of Europe is as the similarity measure of feature descriptors to improve the SIFT feature matching efficiency.Experimental results show that under the condition of keeping the image matching rate and algorithm robust,the method can not only shorten the matching time,but also improve the matching accuracy.