基于模糊集的自适应红外图像边缘锐化算法  

An Adaptive Filter for Infrared Image Edge Enhancement Based on Fuzzy Set

作　　者：管志强[1] 陈钱[1] 王忠林[1] 钱惟贤[1] 胡永生[1] 

机构地区：[1]南京理工大学电光学院441教研室,南京210094

出　　处：《光子学报》2008年第6期1281-1284,共4页Acta Photonica Sinica

基　　金：国防预研基金(40405050303)资助

摘　　要：针对红外图像边缘模糊和非均匀性噪音强的特点,提出了一种基于模糊集的自适应红外图像边缘锐化方法.针对图像边缘细节和噪音难以表示和区分的特点,分别建立噪音、弱边缘和强边缘的模糊特征隶属度函数,并且提取图像信息自适应调整隶属度函数;通过隶属度函数将图像映射到模糊特征平面,由模糊特征平面控制图像边缘锐化系数.该方法不仅能够锐化红外图像边缘,而且改善了传统边缘锐化算法对图像噪音放大的缺点,避免了对强边缘的过渡增强导致图像出现过增强现象,改善了图像质量.In order to improve the infrared-image quality, a kind of adaptive filter based on fuzzy set to enhance the edge without the noise enhancement is advanced. Because the details and the noise of the image is difficult to distinguish, the membership functions of the noise, the weak edge and the strong edge are established and their parameter is adjusted as the image＇s information. And then the image gray-level plane is transformed into fuzzy plane based on the fuzzy membership functions value of each pixel. The sharpening parameters are controlled by the fuzzy plane. As it is shown in experiments, the edge of the image is sharpened and the noise is suppressed.

关 键 词：红外图像 边缘锐化 模糊集 隶属度函数 

分 类 号：TN216[电子电信—物理电子学] TP391[自动化与计算机技术—计算机应用技术]