Image registration method based on improved Harris corner detector  

作　　者：曾琦 刘浏 李建勋 

机构地区：[1]Automation Department,School of Electronic & Information and Electrical Engineering,Shanghai Jiao Tong University

出　　处：《Chinese Optics Letters》2010年第6期573-576,共4页中国光学快报（英文版）

基　　金：supported by the National Natural Science Foundation of China(Nos.60935001 and 60874104);the Space Foundation of Supporting-Technology (No.2008-HT-SHJD003);the Cultivation Fund of the Key Scientific Technical Project Ministry of Education of China(No.706022);the National"973"Project of China(No.2009CB824900),and the Shanghai Key Basic Research Foundation(No.08JC1411800).

摘　　要：Harris corner detector is a classic tool to extract feature.It is stable to illumination change and rotation but unstable to more complicated transform.In order to register images with different viewpoints,we extend Harris corner detector to scale-space to gain invariance to scale change,then we apply affine shape adaptation to the scale invariant point until convergence is reached,giving it invariance to affine transform.With these local features,we use general feature descriptor and matching algorithm to generate matches and then use the matches to calculate the geometric transform matrix,which enables the final registration.Result shows that our algorithm can get more accurate matches than scale invariant feature transform SIFT,and less difference exists between registered images.Harris corner detector is a classic tool to extract feature.It is stable to illumination change and rotation but unstable to more complicated transform.In order to register images with different viewpoints,we extend Harris corner detector to scale-space to gain invariance to scale change,then we apply affine shape adaptation to the scale invariant point until convergence is reached,giving it invariance to affine transform.With these local features,we use general feature descriptor and matching algorithm to generate matches and then use the matches to calculate the geometric transform matrix,which enables the final registration.Result shows that our algorithm can get more accurate matches than scale invariant feature transform SIFT,and less difference exists between registered images.

关 键 词：Detectors Feature extraction Image enhancement Wavelet transforms 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]