一种基于剪切变换和图像增强的融合方法  

A fusion method based on shearlet transform and image enhancement

作　　者：陆万顺[1] 常莉红 冯福存[1] 罗徽 陈新 LU Wan-shun;CHANG Li-hong;FENG Fu-cun;LUO Hui;CHEN Xin(School of Mathematics and Computer Science,Ningxia Normal University,Guyuan 756000,China;School of Mathematics and Information Science,Guangxi University,Nanning 530004,China)

机构地区：[1]宁夏师范学院数学与计算机科学学院,宁夏固原756000 [2]广西大学数学与信息科学学院,广西南宁530004

出　　处：《广西大学学报（自然科学版）》2021年第6期1602-1609,共8页Journal of Guangxi University（Natural Science Edition）

基　　金：宁夏高等学校一流学科建设(教育学学科)研究项目资助(NXYLXK2017B11);宁夏自然科学基金资助(2021AAC03235,2022A0327);宁夏重点研发项目(引才专项)(2019BEB04021);宁夏卓越教师发展研究人才小高地项目资助(20210507)。

摘　　要：为了进一步提高可见光与红外线图像的融合效果,采用剪切波变换和方向滤波建立了一种图像融合方法。通过引导滤波器对可见光图像的场景信息进行增强,提高细节信息;利用剪切波变换对增强后的可见光图像和红外线图像进行多尺度分解,得到不同的低频和高频尺度子带;对低频尺度子带的系数选取能量保护的融合规则,而对高频尺度子带的系数选取PCA的融合规则进行融合;利用剪切波逆变换对融合的低频尺度的子带系数和高频子带的尺度系数进行变换得到融合结果。实验效果表明所提方法能有效地提高融合结果中的细节信息。In order to further improve the fusion effect of visible and infrared images,an image fusion method is established by using shearlet transform and guided filter.The method involves four major steps:The scene information of the visible images is enhanced using the guided filter to improve the detail information;Enhanced visible and infrared images are decomposed to obtain different low-frequency and high-frequency subbands by shearlet transform;The fusion rules are selected for the energy protection in the low-frequency band and the PCA in the high-frequency bands;The fused image reconstructed by taking inverse shearlet transform.Experimental results show that proposed algorithm can improve the detail information in the fused image.

关 键 词：图像融合 剪切波变换 方向滤波 图像增强 

分 类 号：TN911.7[电子电信—通信与信息系统]