A reduced-reference structural similarity approximation for videos corrupted by channel errors

Abstract In this paper we propose a reduced-reference quality assessment algorithm which computes an approximation of the Structural SIMilarity (SSIM) metrics exploiting coding tools provided by the distributed source coding theory. The algorithm has been tested to evaluate the quality of decoded video bitstreams after transmission over error-prone networks. We evaluate the accuracy of the proposed quality assessment algorithm by measuring the Pearson’s correlation coefficient between the structural similarity metrics computed in full-reference mode and the one provided by the proposed reduced-reference algorithm. The proposed reducedreference algorithm achieves good correlation values (higher than 0.85 with packet loss rate equal up to 2.5%). Keywords Reduced reference video quality assessment · Distributed source coding

• Type: Journal
• Year: 2010
• Where: MTA
• Authors: Marco Tagliasacchi, Giuseppe Valenzise, Matteo Naccari, Stefano Tubaro
• Keywords: Algorithm, MTA 2010, Quality Assessment, Structural Similarity