色域映射失真类型图像的质量评价  

Quality assessment method for gamut mapping distortion type images

作　　者：宋超[1,2] 王瑞光[1] 冯英翘[1,2] 陈宇[1] 邓意诚 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,长春130033 [2]华北理工大学信息工程学院,河北唐山063009

出　　处：《吉林大学学报（工学版）》2015年第5期1702-1708,共7页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家科技支撑计划项目(2009BAE7373B00)

摘　　要：针对色域映射失真类型图像,在传统算法的基础上提出了一种新的图像质量评价方法。首先,阐述了该评价方法对图像特征提取的目的及方法,并形成最终的评价公式GMSIM。然后,使用已有的3个色域映射图像集和TID2008图像库对GMSIM算法进行参数拟合和预测准确性分析,对色域映射图像库采用命中率来表征算法性能。实验结果显示:GMSIM算法对色域映射失真图像主观感知的预测准确性比传统的SSIM方法提高约4.5%,但仍有较大的进步空间;在TID2008图像库的预测性能也有所提高。For gamut mapping distortion type images,a new image assessment method was proposed based on traditional algorithms.First,each image feature extraction objective and extraction method were elaborated,and a final assessment formula,named GMSIM,was established based on these features.Then,applying three existing gamut mapping image sets and the TID2008 image library,the parameters of the GMSIM algorithm were fitted,and the prediction accuracy of the algorithm was analyzed.For gamut mapping image sets,hit rate was used as indication of the algorithm performance.Experiment results show that,compared with traditional SSIM method,the proposed GMSIM algorithm prediction accuracy of subjective perceptions for gamut mapping distortion images was improved by about 4.5%,although there is still much room for improvement.The prediction performance for TID2008 image library is also improved to some extent.

关 键 词：信息处理技术 图像质量评价 色域映射 

分 类 号：TN911[电子电信—通信与信息系统]