基于相位一致性和自适应极坐标变换的图像匹配方法  

Image matching method based on phase congruency and adaptive polar transform

作　　者：肖志涛[1] 邱虹[1] 耿磊[1] 张芳[1] 吴骏[1] 

机构地区：[1]天津工业大学电子与信息工程学院,天津300387

出　　处：《河北工业大学学报》2014年第3期21-26,43,共7页Journal of Hebei University of Technology

基　　金：天津市科技支撑计划重点项目(13ZCZDGX02100);天津市高等学校科技发展基金(20120805)

摘　　要：图像匹配是计算机视觉和图像处理中的重要研究内容.本文提出一种基于相位一致性和自适应极坐标变换的图像匹配方法.首先使用相位一致性对参考图像与目标图像进行特征提取,然后进行自适应极坐标变换,最后通过分别计算极径方向和角度方向的投影得出尺度与旋转参数实现图像匹配.实验结果表明,该方法在图像间存在平移、旋转、尺度变换以及部分遮挡的情况下能够准确匹配,并且具有亮度和对比度不变性.Image matching is an important research content in computer vision and image processing. Based on phase congruency and adaptive polar transform, a new image matching method is proposed in this paper. Firstly, the phase congruency is used to extract the features of reference image and target image. Then, the adaptive polar transformation is performed. Finally, by calculating the projection transform, the rotation and scaling parameters are obtained while the image matching is achieved. The experimental results show that the images with translation, rotation, scale and occlusion can be matched accurately and the algorithm is invariant to image brightness and contrast.

关 键 词：图像匹配 自适应极坐标变换 投影变换 相位一致性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]