A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification

TL;DR

This paper introduces a bi-directional curvature-based framework for no-reference image quality assessment that classifies and quantifies image artifacts with high accuracy, leveraging directional image curvature and a two-stage system.

Contribution

The novel contribution is a two-stage system that classifies artifact types and quantifies image quality using a curvature-based measure called ATR, achieving high correlation with human perception.

Findings

Achieves Spearman correlation of -0.93 for Gaussian blur and -0.95 for noise.

Classifies artifact types with over 97% accuracy.

Predicts human quality scores with R2 of 0.892 and RMSE of 5.17 DMOS.

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.