No-reference quality assessment of compressive sensing image recovery

作者：

Highlights：

•

• A no-reference compressive sensing (CS) recovered image quality metric is proposed.

• The proposed metric has a high correlation with the subjective ratings.

• The proposed metric is used for automatic parameter selection for CS image recovery algorithms.

摘要

•A no-reference compressive sensing (CS) recovered image quality metric is proposed.•The proposed metric has a high correlation with the subjective ratings.•The proposed metric is used for automatic parameter selection for CS image recovery algorithms.

论文关键词：Image quality assessment,Compressive sensing,Image sharpness,Singular value decomposition,Natural scene statistics

论文评审过程：Received 24 September 2016, Revised 22 May 2017, Accepted 4 August 2017, Available online 12 August 2017, Version of Record 18 August 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.08.003