基于颜色分量的色域映射图像无参考质量评价算法  

No-Reference Quality Assessment Algorithm for Gamut-Mapped ImagesBased on Color Components

作　　者：余伟 郭志林 胡玲碧 姚捃 YU Wei;GUO Zhi-ling;HU Ling-bi;YAO Jun(Department of Electronic Information&Computer Engineering,The Engineering&Technical College of Chengdu University of Technology,Leshan 614000,China;School of Software and Artificial Intelligence,Chongqing Institute of Engineering,Chongqing 400056,China)

机构地区：[1]成都理工大学工程技术学院电子信息与计算机工程系,乐山614000 [2]重庆工程学院软件与人工智能学院,重庆400056

出　　处：《印刷与数字媒体技术研究》2024年第5期23-32,92,共11页Printing and Digital Media Technology Study

基　　金：重庆市教委科学技术研究计划项目(No.KJQN202201904);乐山市科技局重点研究项目(No.21GZD021)。

摘　　要：色域映射是一种将源图像或设备内的颜色坐标映射到目标设备或图像的方法。在此过程中,由于颜色机制的改变,色域映射图像中颜色信息的丢失将是不可避免的。因此色域映射图像的失真不仅有传统的灰度失真还有颜色失真。目前,色域映射图像的质量评价算法均是将两类失真分开考虑,从灰度域和颜色域分别提取能够表征灰度和颜色失真的特征。但是图像的灰度值是由R、G、B三个颜色分量线性计算而得,图像灰度信息的变化在R、G、B三个颜色分量中均有体现。因此,本研究提出R、G、B颜色信息不仅能表征图像颜色失真也能表征图像灰度失真的设想。基于此设想,直接在R、G、B三个颜色分量上提取质量感知特征,并基于反向传播神经网络训练图像质量评价模型。在三个公开的色域映射图像数据库中进行实验证明,该算法在预测色域映射图像质量方面优于现有图像质量评价算法。Gamut mapping is a way of mapping color information in a source device or image to a target device or image.Because the color mechanisms of different devices are different,the loss of color information is inevitable during the process of gamut mapping.So there are not only gray distortions but also serious color distortions in gamut-mapped images(GMIs).So far,the image quality measures of GMIs extract the features that can represent gray and color distortions from gray domain and color domain respectively.But the gray value of the image is obtained by linear calculation of three color channels(e.g.R,G and B),and the change of the gray information is reflected in the three color channels.Based on this,the assumption was proposed that R,G and B color information can represent not only color distortion but also gray distortion of image in this study.On the basis of this assumption,quality perceived features were extracted from R,G and B color components directly,and the image quality evaluation model was trained based on the back propagation neural network.Finally,experiments on three public GMI databases prove the superiority of this algorithm.

关 键 词：色域映射图像 图像质量评价 颜色失真 灰度失真 质量感知特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TS80[自动化与计算机技术—计算机科学与技术]