Reduced-reference image quality assessment based on distortion families of local perceived sharpness

作者：

Highlights：

• We propose an efficient RR IQA algorithm (S4RR) based on local sharpness analysis.

• S4RR employs the concept of “distortion families”, various sharpness map distance measures, and a two-stage framework for image quality estimation.

• S4RR achieves much better performance than many other state-of-the-art FR/RR IQA algorithms.

摘要

Highlights•We propose an efficient RR IQA algorithm (S4RR) based on local sharpness analysis.•S4RR employs the concept of “distortion families”, various sharpness map distance measures, and a two-stage framework for image quality estimation.•S4RR achieves much better performance than many other state-of-the-art FR/RR IQA algorithms.

论文关键词：Reduced-reference quality assessment,Image quality,Local sharpness,Distortion family

论文评审过程：Received 1 September 2016, Revised 27 March 2017, Accepted 27 March 2017, Available online 2 April 2017, Version of Record 5 April 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.03.020