基于NSCT和改进模糊的遥感图像增强方法  

Enhancement method of remote sensing image based on NSCT and improved fuzzy contrast

作　　者：周飞[1] 贾振红[1] 杨杰[2] Nikola Kasabov ZHOU Fei;JIA Zhenhong;YANG Jie;Nikola Kasabov(College of Information Science and Engineering,Xinjiang University, Urumqi 830046, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200240, China;Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1020, New Zealand)

机构地区：[1]新疆大学信息科学与工程学院,乌鲁木齐830046 [2]上海交通大学图像处理与模式识别研究所,上海200240 [3]新西兰奥克兰理工大学知识工程与发现研究所

出　　处：《计算机工程与应用》2017年第15期206-209,216,共5页Computer Engineering and Applications

基　　金：教育部促进与美大地区科研合作与高层次人才培养项目(No.20101595)

摘　　要：为了解决遥感图像处理过程中噪声放大和图像失真现象,提出了一种结合NSCT和改进模糊对比度的图像增强方法。通过NSCT变换把图像分解成低频子带和若干个高频子带;对低频子带进行线性增强,并利用改进的阈值函数对高频子带进行去噪;随后采用改进的模糊对比度来调整NSCT反变换的系数,以提高图像的整体对比度。实验结果表明,提出的算法的客观指标明显优于其他对比算法,并且视觉效果也得到很大改善。In order to solve the phenomenon of amplifying noise and image distortion in the process of remote sensingimage,an enhancement method is proposed based on NSCT and improved fuzzy contrast.The original image is decomposedinto the NSCT domain with a low-frequency sub-band and several high-frequency sub-bands.Linear transformation isadopted for the coefficients of the low-frequency sub-bands.An adaptive threshold method is used for the removal of highfrequencyimage noise.Subsequently,the improved fuzzy set is used to enhance the global contrast modifying the inversecoefficient of NSCT.Experimental results show that the proposed method not only is superior to other comparativemethods in objective criterions,but also can get better visual effect.

关 键 词：遥感图像 图像增强 NSCT变换 线性变换 自适应阈值 模糊对比度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]