基于数据库和客观方法对夜间雾化增强图像的感知质量评估  

Perceptual quality assessment of night-time haze enhanced images:database and objective method

作　　者：刘倩[1] 李新玥 何周燕 LIU Qian;LI Xinyue;HE-ZHOU Yan(School of Mathematics and Statistics,Ningbo University,Ningbo 315211,China;College of Science&Technology Ningbo University,Ningbo 315300,China;Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 315211,China)

机构地区：[1]宁波大学数学与统计学院,浙江宁波315211 [2]宁波大学科学技术学院,浙江宁波315300 [3]宁波大学信息科学与工程学院,浙江宁波315211

出　　处：《宁波大学学报（理工版）》2024年第4期74-83,共10页Journal of Ningbo University：Natural Science and Engineering Edition

基　　金：浙江省自然科学基金(LQ23F010011).

摘　　要：为提高夜间雾化图像的质量,对夜间雾化增强图像的主客观质量评估进行探索.首先构建夜间雾化增强图像质量评估数据库并进行主观分析,然后提出一种基于夜间成像特性的无参考图像质量评估方法.新方法在辉光图像上提取光散射和颜色特征,再在增强图像上提取雾密度和纹理特征.结果表明,新方法性能优于现有其他先进的无参考图像质量评估方法.To improve the quality of night-time haze images,we study the subjective and objective quality assessment of night-time haze enhanced images.First,a quality assessment database of night-time haze enhanced images is constructed and analyzed subjectively.Subsequently,a novel no-reference image quality assessment method is proposed based on the night-time imaging characteristics.By using the new assessment method,the light scattering and color features in glow images are extracted,and in enhanced images the haze density features and texture features are extracted.The experimental results show that the new method performs better than the other advanced no-reference image quality evaluation methods that are currently available.

关 键 词：夜间雾化增强图像 图像质量评价 光散射加权局部二值模式直方图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]