可见光与红外灰度融合图像感知对比度客观评价  

Perceptual Contrast Metric for Visible and Infrared Gray Fusion Images

作　　者：高绍姝[1] 张晓东[1] 金伟其 GAO Shao-shu;ZHANG Xiao-dong;JIN Wei-qi(College of Computer and Communication Engineering,China University of Petroleum,Qingdao,Shandong 266580,China;MoE Key Laboratory of Photoeleetronic Imaging Technology and System,School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]中国石油大学(华东)计算机与通信工程学院,山东青岛266580 [2]北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081

出　　处：《北京理工大学学报》2018年第7期715-720,共6页Transactions of Beijing Institute of Technology

基　　金：山东省自然科学基金资助项目(ZR2014FP013);青岛市应用基础研究计划项目(14-2-4-115-jch);中央高校基本科研业务费专项资金(16CX02008A);青岛经济技术开发区重点科技发展计划项目(2013-1-37);国家教育部博士学科点专项科研基金资助项目(20131101130002);国家部委重点预研资助项目(40405030302)

摘　　要：如何客观有效地评价融合图像质量,是融合技术发展与装备应用面临的一个关键问题.图像对比度是衡量双波段灰度融合质量的一项重要的评价指标.针对目前的图像对比度客观计算模型没有充分反映人眼视觉特性,从而影响模型计算结果与人眼视觉感受的一致性的问题.在各向同性局部对比度计算模型基础上,引入人眼视觉的亮度掩盖特性,提出图像感知对比度客观评价模型.使用模拟灰度图像以及人眼主观评价实验得到的15组不同真实场景融合图像的对比度评价数据来验证客观计算模型.结果表明,相比于4种经典的对比度客观评价模型,建立的图像感知对比度模型评价结果更符合人眼视觉感受,可以有效实现双波段灰度融合图像感知对比度的客观评价.To evaluate the fusion image quality scientifically for fusion technology research and equipment applications,image contrast was taken as an important quality metric of dual-band gray fusion images.To solve the problem in the existing contrast metrics,unconsidering human visual system and affecting coherence between the predictions and the human perceptions,an objective perceptual contrast metric was proposed based on isotropic local contrast model as well as the introduction of the human luminance masking effect.The simulated gray images and the observer evaluation scores for 15 groups of real scene gray fusion images were used to test the proposed model.Experimental results show that the proposed perceptual contrast metric is more closely matched to the human vision perception than existing methods and can evaluate the dualband gray fusion image perceptual contrast effectively.

关 键 词：灰度融合 图像对比度 客观模型 人眼视觉特性 

分 类 号：TN219[电子电信—物理电子学]