基于图像内容对比感知的图像质量客观评价  

Objective assessment of image quality based on image content contrast perception

作　　者：姚军财 申静[1] Yao Jun-Cai;Shen Jing(School of Computer Engineering,Nanjing Institute of Technology,Nanjing 211167,China;School of Physics and Telecommunication Engineering,Shaanxi University of Technology,Hanzhong 723000,China;School of Information and Communications Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]南京工程学院计算机工程学院,南京211167 [2]陕西理工大学物理与电信工程学院,汉中723000 [3]西安交通大学信息与通信工程学院,西安710049

出　　处：《物理学报》2020年第14期281-296,共16页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:61301237);南京工程学院人才引进科研启动基金(批准号:YKJ201981);陕西省自然科学基金(批准号:2019JM-213);陕西省科技新星计划(批准号:2015KJXX-42)资助的课题.

摘　　要：为了提出性能优异的图像质量评价(IQA)模型,本文基于人类视觉感知特性和图像的灰度梯度、局部对比度和清晰度特征,提出了一种基于图像内容对比感知的IQA方法.在该方法中,首先结合视觉感知特性,基于物理学中对比度定义,提出一种图像质量定义及其值计算方法;之后,基于灰度梯度共生矩阵,提出一种图像灰度梯度熵的概念及其值的计算方法,并基于图像灰度梯度熵、局部对比度和清晰度,提出一种图像内容及其视觉感知的描述方法;最后,基于图像内容特征和图像质量定义,综合分析,提出IQA方法及其数学模型.并且采用5个开源图像数据库中的119幅参考图像和6395幅失真图像对其进行了仿真测试,同时分析和探讨了52种失真类型对IQA的影响;另外,为了说明所提IQA模型的优势,将其与现有的7个典型IQA模型,从精度、复杂性和泛化性能上进行了对比分析.实验结果表明,所提IQA模型的精度PLCC值在5个数据库中最低可以实现0.8616,最高可达到0.9622,其性能综合效益优于7个现有IQA模型.研究结果表明,所提IQA方法是有效的、可行的,所提IQA模型是一个性能优异的IQA模型.Image quality assessment(IQA)plays a very important role in acquiring,storing,transmitting and processing image and video.Using the characteristics of human visual perception and the features of the gray,gradient,local contrast,and blurring of image,an IQA method based on the image content contrast perception is proposed in the paper,which is called MPCC.In the proposed method,firstly,combining with the characteristics of human visual perception,based on the definition of the contrast in physics,a novel definition for image quality and its calculation method are proposed.Then,based on the gray gradient co-occurrence matrix,a novel concept,namely the gray-gradient entropy of image,and its calculation method,are proposed.And based on the gray-gradient entropy,local contrast and blurring of image,a method of describing the image content and their visual perception are proposed.Finally,based on the image content features and the image quality definition,an IQA method and its mathematical model are proposed by comprehensive analysis.Further,the proposed IQA model MPCC is tested by using 119 reference images and 6395 distorted images from the five open image databases(LIVE,CSIQ,TID2008,TID2013 and IVC).Moreover,the influences of the 52 distortion types on IQA are analyzed.In addition,in order to illustrate the advantages of the MPCC model,it is compared with the seven existing typical IQA models in terms of the accuracy,complexity and generalization performance of model.The experimental results show that the accuracy PLCC of the MPCC model can achieve 0.8616 at lowest and 0.9622 at most in the five databases;among the 52 distortion types,the two distortion types,namely the change of color saturation and the local block-wise distortions of different intensity,have the greatest influence on IQA,and the accuracy PLCC values of the seven existing IQA models are almost all below 0.6,but the PLCC of the MPCC model can reach more than 0.68;and the comprehensive benefit of the performance of the MPCC model is better than those

关 键 词：图像质量评价 人类视觉特性 图像内容 对比度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]