Hybrid Image Resolution Quality Metric (HIRQM):A Comprehensive Perceptual Image Quality Assessment Framework

TL;DR

Traditional IQA metrics often fail to reflect perceptual quality under complex distortions. HIRQM fuses three cues—PDF for local statistics, MFS for multi-scale structure, and HDIF for semantic similarity—through a dynamic weighting mechanism to produce a single perceptual score. The final score is computed multiplicatively as $HIRQM = PDF^{w_1} \cdot MFS^{w_2} \cdot HDIF^{w_3}$, with softmax-derived weights $w_1,w_2,w_3$; this enables adaptive emphasis across image types. Empirical validation on TID2013 and LIVE shows superior correlation with human judgments (Pearson ≈0.92, Spearman ≈0.90) and robustness to noise, blur, and compression, supporting practical deployment in compression, restoration, and image processing workflows.

Abstract

Traditional image quality assessment metrics like Mean Squared Error and Structural Similarity Index often fail to reflect perceptual quality under complex distortions. We propose the Hybrid Image Resolution Quality Metric (HIRQM), integrating statistical, multi-scale, and deep learning-based methods for a comprehensive quality evaluation. HIRQM combines three components: Probability Density Function for local pixel distribution analysis, Multi-scale Feature Similarity for structural integrity across resolutions, and Hierarchical Deep Image Features using a pre-trained VGG16 network for semantic alignment with human perception. A dynamic weighting mechanism adapts component contributions based on image characteristics like brightness and variance, enhancing flexibility across distortion types. Our contributions include a unified metric and dynamic weighting for better perceptual alignment. Evaluated on TID2013 and LIVE datasets, HIRQM achieves Pearson and Spearman correlations of 0.92 and 0.90, outperforming traditional metrics. It excels in handling noise, blur, and compression artifacts, making it valuable for image processing applications like compression and restoration.

Figures (2)

• Figure 1: HIRQM system architecture.
• Figure 2: Line chart comparing Pearson and Spearman correlations of MSE, SSIM, VIF, FSIM, and HIRQM across TID2013, LIVE, and Waterloo Exploration datasets.