基于结构相似度的图像融合客观评价指标  

Evaluation Endex for Emage Fusion based on Structural Similarity

作　　者：谭惜姿 陆伟[1] LV Kang-fei(Department of Physics and Electronics,Huaiyin Normal University,Huaian Jiangsu 223300,China)

机构地区：[1]淮阴师范学院计算机科学与技术学院,江苏淮安223300

出　　处：《淮阴师范学院学报（自然科学版）》2018年第3期235-239,共5页Journal of Huaiyin Teachers College;Natural Science Edition

基　　金：国家自然科学基金项目(61243242);江苏省大学生实践创新训练计划项目(201810323004Z)

摘　　要：针对目前图像融合客观评价指标不能很好地解决客观评价与主观视觉感知相符和的问题,提出了基于结构相似度与直方图均衡化相结合的红外与可见光图像融合客观评价指标.实验结果表明,与现有的经典客观评价指标相比,本文提出的方法更能正确地反映视觉感知,可用于红外与可见光图像融合客观评价.Aiming at the objective fusion evaluation index has been not well solve the problem of the objective evaluation results was not consistent with the subjective visual perception,we use SSIM index and the degree of the histogram equalization to construct a novel infrared and visible image fusion objective evaluation index.The experimental results show that the method proposed in this paper can reflect visual perception more accurately than the existing traditional objective evaluation indexes,and can be used for the objective evaluation of infrared and visible images fusion.

关 键 词：图像融合 评价指标 结构相似度 直方图均衡化 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术]