Estimation of distortion sensitivity for visual quality prediction using a convolutional neural network

Sebastian Bosse, Sören Becker, Klaus Muller, Wojciech Samek, Thomas Wiegand

Research output: Contribution to journalArticle

Abstract

The PSNR and MSE are the computationally simplest and thus most widely used measures for image quality, although they correlate only poorly with perceived visual quality. More accurate quality models that rely on processing on both the reference and distorted image are potentially difficult to integrate in time-critical communication systems where computational complexity is disadvantageous. This paper derives the concept of distortion sensitivity as a property of the reference image that compensates for a given computational quality model a potential lack of perceptual relevance. This compensation method is applied to the PSNR and leads to a local weighting scheme for the MSE. Local weights are estimated by a deep convolutional neural network and used to improve the PSNR in a computationally graceful distribution of computationally complex processing to the reference image only. The performance of the proposed estimation approach is evaluated on LIVE, TID2013 and CSIQ databases and shows comparable or superior performance compared to benchmark image quality measures.

Original languageEnglish
JournalDigital Signal Processing: A Review Journal
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Image quality
Neural networks
Processing
Computational complexity
Communication systems
Compensation and Redress

Keywords

  • Deep learning
  • Distortion sensitivity
  • Image quality assessment
  • Perceptual coding
  • Visual perception

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Estimation of distortion sensitivity for visual quality prediction using a convolutional neural network. / Bosse, Sebastian; Becker, Sören; Muller, Klaus; Samek, Wojciech; Wiegand, Thomas.

In: Digital Signal Processing: A Review Journal, 01.01.2018.

Research output: Contribution to journalArticle

Bosse, Sebastian ; Becker, Sören ; Muller, Klaus ; Samek, Wojciech ; Wiegand, Thomas. / Estimation of distortion sensitivity for visual quality prediction using a convolutional neural network. In: Digital Signal Processing: A Review Journal. 2018.
@article{b02b041aff304d0fbeb8049f9dba75f2,
title = "Estimation of distortion sensitivity for visual quality prediction using a convolutional neural network",
abstract = "The PSNR and MSE are the computationally simplest and thus most widely used measures for image quality, although they correlate only poorly with perceived visual quality. More accurate quality models that rely on processing on both the reference and distorted image are potentially difficult to integrate in time-critical communication systems where computational complexity is disadvantageous. This paper derives the concept of distortion sensitivity as a property of the reference image that compensates for a given computational quality model a potential lack of perceptual relevance. This compensation method is applied to the PSNR and leads to a local weighting scheme for the MSE. Local weights are estimated by a deep convolutional neural network and used to improve the PSNR in a computationally graceful distribution of computationally complex processing to the reference image only. The performance of the proposed estimation approach is evaluated on LIVE, TID2013 and CSIQ databases and shows comparable or superior performance compared to benchmark image quality measures.",
keywords = "Deep learning, Distortion sensitivity, Image quality assessment, Perceptual coding, Visual perception",
author = "Sebastian Bosse and S{\"o}ren Becker and Klaus Muller and Wojciech Samek and Thomas Wiegand",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.dsp.2018.12.005",
language = "English",
journal = "Digital Signal Processing: A Review Journal",
issn = "1051-2004",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Estimation of distortion sensitivity for visual quality prediction using a convolutional neural network

AU - Bosse, Sebastian

AU - Becker, Sören

AU - Muller, Klaus

AU - Samek, Wojciech

AU - Wiegand, Thomas

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The PSNR and MSE are the computationally simplest and thus most widely used measures for image quality, although they correlate only poorly with perceived visual quality. More accurate quality models that rely on processing on both the reference and distorted image are potentially difficult to integrate in time-critical communication systems where computational complexity is disadvantageous. This paper derives the concept of distortion sensitivity as a property of the reference image that compensates for a given computational quality model a potential lack of perceptual relevance. This compensation method is applied to the PSNR and leads to a local weighting scheme for the MSE. Local weights are estimated by a deep convolutional neural network and used to improve the PSNR in a computationally graceful distribution of computationally complex processing to the reference image only. The performance of the proposed estimation approach is evaluated on LIVE, TID2013 and CSIQ databases and shows comparable or superior performance compared to benchmark image quality measures.

AB - The PSNR and MSE are the computationally simplest and thus most widely used measures for image quality, although they correlate only poorly with perceived visual quality. More accurate quality models that rely on processing on both the reference and distorted image are potentially difficult to integrate in time-critical communication systems where computational complexity is disadvantageous. This paper derives the concept of distortion sensitivity as a property of the reference image that compensates for a given computational quality model a potential lack of perceptual relevance. This compensation method is applied to the PSNR and leads to a local weighting scheme for the MSE. Local weights are estimated by a deep convolutional neural network and used to improve the PSNR in a computationally graceful distribution of computationally complex processing to the reference image only. The performance of the proposed estimation approach is evaluated on LIVE, TID2013 and CSIQ databases and shows comparable or superior performance compared to benchmark image quality measures.

KW - Deep learning

KW - Distortion sensitivity

KW - Image quality assessment

KW - Perceptual coding

KW - Visual perception

UR - http://www.scopus.com/inward/record.url?scp=85059095983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059095983&partnerID=8YFLogxK

U2 - 10.1016/j.dsp.2018.12.005

DO - 10.1016/j.dsp.2018.12.005

M3 - Article

JO - Digital Signal Processing: A Review Journal

JF - Digital Signal Processing: A Review Journal

SN - 1051-2004

ER -