Image Registration Using a Complete Polar Transform  

作　　者：ZHAO Wei HUANG Lidong WANG Jun SUN Zebin 

机构地区：[1]Institute of Electronic and Information Engineering, Beihang University

出　　处：《Chinese Journal of Electronics》2014年第2期403-408,共6页电子学报（英文版）

基　　金：partly supported by National Natural Science Foundation of China-Royal Society of Edinburgh Joint Project:Next Generation Neurobiologically Inspired Autonomous Visual Surveillance Systems(No.61211130210)

摘　　要：Image registration is widely used in image processing. Researchers have introduced image registration techniques based on the log-polar transform for its rotation and scale invariant properties. It suffers from nonuniform sampling which makes the registration results susceptible to interference. To address the problems of traditional log-polar transform, a Complete polar transform(CPT) method is proposed, which samples the image evenly to preserve the whole information of original image.An innovative pro jection transform is applied after CPT to obtain the rotation invariant property. We pre-matched feature points using the Scale invariant feature transform(SIFT)algorithm and re-matched them based on CPT to improve matching speed and accuracy. Experimental results show that the proposed method is accurate and robust to noise and alteration.Image registration is widely used in im- age processing. Researchers have introduced image reg- istration techniques based on the log-polar transform for its rotation and scale invariant properties. It suffers from nonuniform sampling which makes the registration results susceptible to interference. To address the problems of traditional log-polar transform, a Complete polar trans- form （CPT） method is proposed, which samples the image evenly to preserve the whole information of original image. An innovative projection transform is applied after CPT to obtain the rotation invariant property. We pre-matched feature points using the Scale invariant feature transform （SIFT）algorithm and re-matched them based onCPT to improve matching speed and accuracy. Experimental re- sults show that the proposed method is accurate and ro- bust to noise and alteration.

关 键 词：Image registration  Polar transform  Feature points match Scale invariant feature transform （SIFT）. 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP335.1[自动化与计算机技术—计算机科学与技术]