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 language | English |
|---|---|
| Journal | Digital Signal Processing: A Review Journal |
| DOIs | |
| Publication status | Accepted/In press - 2018 Jan 1 |
Fingerprint
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 journal › Article
}
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 -