🤖 AI Summary
To address insufficient artifact-type discrimination and quantification accuracy in no-reference image quality assessment (NR-IQA), this paper proposes a novel framework based on directional image curvature analysis. It pioneers the use of bidirectional curvature difference responses to distinguish degradation types—including blur and noise—and introduces an adjustable-threshold anisotropic texture richness (ATR) metric for pixel-level degradation modeling. A classification–regression two-stage system is developed: the first stage achieves 97.2% artifact classification accuracy; the second stage maps ATR to perceptual quality scores, attaining R² = 0.892 and RMSE = 5.17 DMOS (7.4% of the full scale) on a composite dataset. The method achieves Spearman correlation coefficients of −0.93 and −0.95 with human judgments for Gaussian blur and white noise, respectively—demonstrating superior discriminability and perceptual consistency.
📝 Abstract
This work presents a novel framework for No-Reference Image Quality Assessment (NR-IQA) founded on the analysis of directional image curvature. Within this framework, we define a measure of Anisotropic Texture Richness (ATR), which is computed at the pixel level using two tunable thresholds -- one permissive and one restrictive -- that quantify orthogonal texture suppression. When its parameters are optimized for a specific artifact, the resulting ATR score serves as a high-performance quality metric, achieving Spearman correlations with human perception of approximately -0.93 for Gaussian blur and -0.95 for white noise on the LIVE dataset. The primary contribution is a two-stage system that leverages the differential response of ATR to various distortions. First, the system utilizes the signature from two specialist ATR configurations to classify the primary artifact type (blur vs. noise) with over 97% accuracy. Second, following classification, it employs a dedicated regression model mapping the relevant ATR score to a quality rating to quantify the degradation. On a combined dataset, the complete system predicts human scores with a coefficient of determination (R2) of 0.892 and a Root Mean Square Error (RMSE) of 5.17 DMOS points. This error corresponds to just 7.4% of the dataset's total quality range, demonstrating high predictive accuracy. This establishes our framework as a robust, dual-purpose tool for the classification and subsequent quantification of image degradation.