A New Approach to Video Quality Assessment Based on Human Perception and Fusion

doi:10.11834/jig.20091043

Views : 0 下载量: 224 CSCD: 0

PDF
Export
Share
Collection
Album

A New Approach to Video Quality Assessment Based on Human Perception and Fusion
Vol. 14, Issue 10, Pages: 2165(2009)
Published：2009
DOI： 10.11834/jig.20091043
稿件说明：

移动端阅览

DOI：

A New Approach to Video Quality Assessment Based on Human Perception and Fusion[J]. Journal of Image and Graphics, 2009, 14(10): 2165. DOI： 10.11834/jig.20091043.

摘要

提出了一种结合人眼视觉特性（HVS）和信息融合的视频质量评价新方法。该方法是在结构相似（SSIM）方法基础之上，融合了人眼几个主要视觉特性，如对比敏感度、多通道、视觉掩盖、视觉非线性等。新方法具有SSIM算法简单、高效等特性，同时又满足人眼视觉特性，更好地反映了人的主观感受。通过VQEG Phase I测试数据集的实验结果证明，该方法在非线性回归后相关系数、斯皮尔曼相关系数、线外率等指标均优于传统的其他视频质量评价算法，有效地提高了视频质量评价的主客观一致性。

Abstract

The paper presents an new approach to video quality assessment based on human perception and fusion. In the proposed method

the SSIM values are calculated with the different weighted values fused visual characteristics including contrast sensitivity

multi-channel structure

visual masking and so on. The method has the same properties of simplicity and efficiency as that of the SSIM method. And it is more suitable for perceived characteristics due to fusing HVS. The experimental results show that the method can reflect people’s subjective feelings in a better way and is better than other traditional methods in fitting M2(correlation coefficient of Non-linear regression)

M3(spearman rank)

M4(outlier ratio)of VQEG Phase I MOS.