EVALUATING NON-REFERENCE IMAGE QUALITY METRICS FOR AI-GENERATED IMAGES
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
The exponential growth of AI-generated images produced by Generative Adversarial Networks (GANs) and diffusion-based models has created an urgent need for reliable image quality evaluation systems. Traditional full-reference metrics such as PSNR and SSIM require pristine ground-truth images, which are unavailable for generative outputs. This limitation necessitates robust Non- Reference Image Quality Assessment (NR-IQA) frameworks.
This paper presents VisionIQ Pro, a hybrid multi- tiered visual quality assessment system that integrates handcrafted statistical signal metrics with deep perceptual Natural Scene Statistics (NSS) metrics such as BRISQUE and NIQE. The system constructs a fused Image Quality Vector and uses a Random Forest regression model trained on KonIQ-10k and LIVE datasets to predict Mean Opinion Score (MOS). Additionally, the framework incorporates Explainable AI through Sobel-based sharpness density mapping and actionable feedback logic.
Experimental analysis demonstrates strong correlation (PLCC > 0.85) with human subjective perception. The proposed system serves as a scalable, interpretable, and production-ready solution for automated auditing of AI-generated and real-world images
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Kannan, B. M. & Dhanalakshmi, K. (2026). Evaluating Non-Reference Image Quality Metrics for AI-Generated Images. International Journal of Science, Strategic Management and Technology, 02(03). https://doi.org/10.55041/ijsmt.v2i3.276
Kannan, B., and K. Dhanalakshmi. "Evaluating Non-Reference Image Quality Metrics for AI-Generated Images." International Journal of Science, Strategic Management and Technology, vol. 02, no. 03, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i3.276.
Kannan, B., and K. Dhanalakshmi. "Evaluating Non-Reference Image Quality Metrics for AI-Generated Images." International Journal of Science, Strategic Management and Technology 02, no. 03 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i3.276.
References
2.Duan J. Improving radiotherapy workflow: evaluation and implementation of deep learning auto-segmentation in a multi-user environment, and development of automatic contour quality assurance system. UKnowledge. 2023.
3.Gatt A, Krahmer Survey of the State of the Art in Natural Language Generation: core tasks, applications and evaluation. 2017. Available from: https://core.ac.uk/download/93183864.pdf.
4.Hosang J, Benenson R, Dollar P, Schiele B. What makes for effective detection proposals? IEEE Trans Pattern Anal Mach Intell (TPAMI). 2015;38(4):814-830.
5.Horvitz E, Kamar E, Nushi B. Towards accountable AI: hybrid human-machine analyses for characterizing system failure. 2018.
6.Tiotsop F, Optimizing perceptual quality prediction models for multimedia processing systems. Italy, 2022.
7.Bardhan R, Ramsankaran RAAJ, Sathyakumar V. Geospatial approach for assessing spatiotemporal dynamics of urban green space distribution among neighbourhoods. Urban Forest Urban Green. 2020;49:126630.
8.Mirkhan Enhancing point cloud quality assessment with grouped convolutions: a streamlined approach inspired by COPP Net. 2024.
9.Bonneel N, Garces E, Lalonde J-F, Meka Unsupervised deep single-image intrinsic decomposition using illumination varying image sequences. 2018.
10.Miyata T. Interpretable image quality assessment via CLIP with multiple antonym-prompt pairs. arXiv:2308.13094. 2023.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
