MDID: A multiply distorted image database for image quality assessment

作者：

Highlights：

• The images are multiply distorted with random types and levels of distortions.

• We propose a subjective evaluation scheme based on pair comparison sorting.

• The initial parameters are estimated for regression through mathematical derivation.

• Experiments validate the reasonability and challenges of this database.

摘要

•The images are multiply distorted with random types and levels of distortions.•We propose a subjective evaluation scheme based on pair comparison sorting.•The initial parameters are estimated for regression through mathematical derivation.•Experiments validate the reasonability and challenges of this database.

论文关键词：Image database,Image quality assessment,Multiply distorted images,Pair comparison sorting,Nonlinear regression

论文评审过程：Received 16 July 2015, Revised 19 July 2016, Accepted 22 July 2016, Available online 26 July 2016, Version of Record 5 August 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.033