Information-based reduced reference image quality assessment incorporating non-tensor product wavelet filter banks  

作　　者：Yong Ding Yuan Zhang Xiaolang Yan Andrey S.Krylov 

机构地区：[1]Institute of VLSI Design,Zhejiang University [2]Laboratory of Mathematical Methods of Image Processing,Lomonosov Moscow State University,Moscow,Russia

出　　处：《Chinese Science Bulletin》2014年第16期1917-1924,共8页

基　　金：supported by the National Science & Technology Support Program (2013BAH03B01);Special Project on the Integration of Industry,Education and Research of Guangdong Province (2012A090300017)

摘　　要：To achieve the better performance of image quality assessment,this paper develops an informationbased scheme.First,visual maps that contain visual information are extracted by non-tensor product wavelet filter banks at different scales.Subsequently,to model visual difference(VD)caused by image degradations,the variation of information entropy between distorted and reference images is employed.Then the final visual quality is calculated with the VDs at each scale.In experiments,evaluation results show that it performs very well in terms of high accuracy of image quality measurement as well as low data rate.To achieve the better performance of image quality assessment, this paper develops an information-based scheme. First, visual maps that contain visual information are extracted by non-tensor product wavelet filter banks at different scales. Subsequently, to model visual difference （VD） caused by image degradations, the variation of information entropy between distorted and reference images is employed. Then the final visual quality is calculated with the VDs at each scale. In experiments, evaluation results show that it performs very well in terms of high accuracy of image quality measurement as well as low data rate.

关 键 词：图像质量评价 非张量积小波 视觉信息 滤波器组 基础 数据传输速率 退化模型 视觉质量 

分 类 号：TN713[电子电信—电路与系统]