基于相位一致性变换的红外图像区域匹配算法研究  

INFRARED IMAGE REGION MATCHING ALGORITHMS BASED ON PHASE CONGRUENCY TRANSFORMATION

作　　者：郭龙源[1] 卢阿丽[1] 杨静宇[1] 

机构地区：[1]南京理工大学计算机科学与技术系,江苏南京210094

出　　处：《红外与毫米波学报》2009年第1期35-37,45,共4页Journal of Infrared and Millimeter Waves

基　　金：国防基础研究项目基金(J1500C002)

摘　　要：由于红外图像具有高噪声、低分辨率的特点,这使得在红外图像中使用基于区域的匹配方法很难取得较好的视差图.在分析了经相位一致性变换后图像的特征后,提出了一种基于区域的匹配方法.即先对图像进行相位一致性变换,再利用变换后图像进行区域匹配.试验结果表明,相位一致性变换后的新图像,噪声得到了较好的抑制,特征更加明显.对变换后的图像采用区域匹配的方法,可以得到较好的匹配效果.Infrared images have higher noise and lower resolution than visible images. This makes it more difficult to achieve a better disparity image in infrared images by using the method based on region matching. After analyzing the phase congruency transformed image, a new region matching method was presented. First, the images were transformed by phase congruency. Next, the images were matched based on region correlation. The experimental result indicates that the noise of images is restrained and the feature is more distiinct after phase congruency. The better matching results can be obtained after we use the region correlation on the changed images.

关 键 词：计算机视觉 相位一致性 区域匹配 红外图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]