English

Empirical evaluation of full-reference image quality metrics on MDID database

Image and Video Processing 2019-10-08 v2 Computer Vision and Pattern Recognition

Abstract

In this study, our goal is to give a comprehensive evaluation of 32 state-of-the-art FR-IQA metrics using the recently published MDID. This database contains distorted images derived from a set of reference, pristine images using random types and levels of distortions. Specifically, Gaussian noise, Gaussian blur, contrast change, JPEG noise, and JPEG2000 noise were considered.

Keywords

Cite

@article{arxiv.1910.01050,
  title  = {Empirical evaluation of full-reference image quality metrics on MDID database},
  author = {Domonkos Varga},
  journal= {arXiv preprint arXiv:1910.01050},
  year   = {2019}
}
R2 v1 2026-06-23T11:32:55.685Z