结合人眼视觉综合感知差与r-g色域峰值偏差的彩色图像客观评价方法  

An Approach to Color Image Quality Objective Assessment by Combining Human Vision Based General Perceptive Deviation and r-g Chromatic Peak Value Offset

作　　者：高昆[1] 程新满[1] 吕丽丽[1] 邵晓光[1] 

机构地区：[1]北京理工大学光电成像技术与系统教育部重点实验室,微光夜视技术国家级重点实验室,北京100081

出　　处：《北京理工大学学报》2012年第3期286-290,295,共6页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(60702017);国家部委科技重点实验室基金资助项目(J20110502);航空基金资助项目(20100112002)

摘　　要：针对图像色彩复原应用中对彩色图像质量评价的需求,在图像灰度直方图累计分布差的基础上,通过引入人眼视觉敏感度等修正因子,得到了直方图感知差的评价方法,并与图像的信息熵和平均梯度指标相结合,提出了基于综合感知差的评价方法以及将综合感知差与色域峰值偏差结合的无参考型彩色图像评价新方法.构建了不同光照条件下的标准彩色图像测试数据库,通过与传统的客观评价标准相比,新方法在图像亮度感知、色调信息和图像综合质量等方面均表现出与主观评价更高的一致性.To meet the requirement of color image quality assessment in applications of the image color restoration,the index of histogram perceptive deviation evaluation,based on the histogram cumulative distributions of images＇ grey information,is generated by introducing such correction factors as human vision sensitivity,etc.Then general perceptive deviation algorithm is proposed via combining histogram perceptive deviation with entropy and average gradient values.A novel no-reference objective image quality assessment approach is achieved by associating general perceptive deviation parameter with r-g chromatic peak value offset parameter.To test the performance of the algorithm above,a standard color image database under different illumination conditions is established.Compared with the usual objective evaluation indexes,the proposed approach is more coincident with the subjective assessment method in the brightness perception,hue value and synthetic quality.

关 键 词：彩色图像质量评价 综合感知差 r-g色域峰值偏差 人眼视觉系统 

分 类 号：O436[机械工程—光学工程]