Perceptual image quality assessment through spectral analysis of error representations

作者：

Highlights：

• SUMMER is an image quality estimator based on spectral analysis of error signals.

• Spectral analysis is performed over multiple scales and color channels.

• Frequency-based weights are extracted to align spectral analysis scores.

• Mean error spectrum increases as visual degradations become more severe.

• SUMMER significantly outperforms majority of the benchmarked algorithms.

摘要

•SUMMER is an image quality estimator based on spectral analysis of error signals.•Spectral analysis is performed over multiple scales and color channels.•Frequency-based weights are extracted to align spectral analysis scores.•Mean error spectrum increases as visual degradations become more severe.•SUMMER significantly outperforms majority of the benchmarked algorithms.

论文关键词：Full-reference image quality assessment,Visual system,Error spectrum,Spectral analysis,Color perception,Multi-resolution

论文评审过程：Received 15 August 2017, Revised 8 September 2018, Accepted 10 September 2018, Available online 14 September 2018, Version of Record 22 September 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.09.005