Through BrokenEyes: How Eye Disorders Impact Face Detection?

TL;DR

This paper introduces a computational framework to simulate five common eye disorders and analyzes their effects on face detection models, revealing how visual impairments disrupt neural-like feature representations.

Contribution

The study develops the BrokenEyes system to model eye disorders and assesses their impact on deep learning face detection, providing new insights into visual processing under impairment conditions.

Findings

Cataract and glaucoma cause significant disruptions in feature maps.

Activation energy and cosine similarity effectively quantify visual distortions.

Disorders impact neural-like representations in face detection models.

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.