Through BrokenEyes: How Eye Disorders Impact Face Detection?

2026-02-26

AI Summary

This study investigates the impact of common ocular diseases on feature representation and detection performance in face recognition systems. To this end, we propose BrokenEyes, a computational framework that, for the first time, integrates visual perturbations caused by five prevalent eye conditions with deep neural network feature analysis. The framework quantifies feature map disturbances using activation energy and cosine similarity. Experiments on both human and non-human datasets demonstrate that cataracts and glaucoma induce the most significant degradation in deep features, revealing a quantitative relationship between visual impairment and diminished model representational capacity. These findings offer novel insights for designing more robust face recognition systems resilient to ocular pathologies.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Representation Learning
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Vision disorders significantly impact millions of lives, altering how visual information is processed and perceived. In this work, a computational framework was developed using the BrokenEyes system to simulate five common eye disorders: Age-related macular degeneration, cataract, glaucoma, refractive errors, and diabetic retinopathy and analyze their effects on neural-like feature representations in deep learning models. Leveraging a combination of human and non-human datasets, models trained under normal and disorder-specific conditions revealed critical disruptions in feature maps, particularly for cataract and glaucoma, which align with known neural processing challenges in these conditions. Evaluation metrics such as activation energy and cosine similarity quantified the severity of these distortions, providing insights into the interplay between degraded visual inputs and learned representations.

Problem

• eye disorders
• face detection
• feature representation
• deep learning
• visual impairment

Innovation

• BrokenEyes
• eye disorders simulation
• feature representation disruption
• deep learning robustness
• visual impairment modeling