MUG: A Parameterless No-Reference JPEG Quality Evaluator Robust to Block Size and Misalignment

TL;DR

This paper introduces MUG, a simple, parameterless no-reference JPEG quality metric that is robust to block size and misalignment, performing comparably to state-of-the-art methods without requiring training.

Contribution

The paper proposes MUG, a novel no-reference JPEG quality assessment metric that is independent of block size and cropping, and introduces MUG+ for enhanced stability.

Findings

MUG performs comparably to state-of-the-art indices.

MUG's performance remains stable on cropped images.

MUG does not require training or parameter tuning.

Abstract

In this letter, a very simple no-reference image quality assessment (NR-IQA) model for JPEG compressed images is proposed. The proposed metric called median of unique gradients (MUG) is based on the very simple facts of unique gradient magnitudes of JPEG compressed images. MUG is a parameterless metric and does not need training. Unlike other NR-IQAs, MUG is independent to block size and cropping. A more stable index called MUG+ is also introduced. The experimental results on six benchmark datasets of natural images and a benchmark dataset of synthetic images show that MUG is comparable to the state-of-the-art indices in literature. In addition, its performance remains unchanged for the case of the cropped images in which block boundaries are not known. The MATLAB source code of the proposed metrics is available at https://dl.dropboxusercontent.com/u/74505502/MUG.m and https://dl.dropboxusercontent.com/u/74505502/MUGplus.m.