Full-Reference Video Quality Assessment using Structural Similarity (SSIM) Index

Abstract

Video Quality Assessment is one of the key words in the field of Quality of Service (QoS) for mobile phones, today. The goal of video quality assessment is to evaluate if a distorted video is of a good quality by quantifying the difference between the original and distorted video. To assess the video quality of an arbitrary distorted or compressed video, the visual features of the distorted video are compared with those of the original video. Objective video quality measures play important roles in a variety of video processing applications, such as compression, communication, printing, analysis, registration, restoration, enhancement and watermarking. Most proposed quality assessment approaches in the literature are error sensitivity-based methods. In this paper, we follow a new algorithm Structural Similarity (SSIM) Index in designing video quality metrics, which uses structural distortion as an estimate of perceived visual distortion. This algorithm is simple, straight forward, makes real time implementation easy, very consistent relation with the subjective measures and delivers more accurate results compared to other objective video quality measures MSE and PSNR and computationally efficient for full-reference (FR) video quality assessment.