Empirical evaluation of full-reference image quality metrics on MDID database
arXiv:1910.01050
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.
References in corpus (6)
- Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
- A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment
- Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator
- Perceptual Image Quality Assessment through Spectral Analysis of Error Representations
- PerSIM: Multi-resolution Image Quality Assessment in the Perceptually Uniform Color Domain
- CSV: Image Quality Assessment Based on Color, Structure, and Visual System