Conjunctivitis of Eye Detection Using CNN

Abstract

Conjunctivitis, commonly known as "pink eye," is a highly contagious inflammation of the conjunctiva that affects millions globally each year. Early and accurate detection is crucial for effective treatment and to prevent widespread transmission. Traditional diagnosis relies heavily on physical examination and clinical expertise, which may be time-consuming and prone to human error. This paper proposes an automated Conjunctivitis detection system using Convolutional Neural Networks (CNN), a deep learning technique well-suited for image classification tasks. The proposed model is trained on a curated dataset of eye images labeled as normal or conjunctivitis-infected. The CNN architecture extracts hierarchical visual features and learns patterns associated with conjunctivitis, enabling robust classification. The system achieves high accuracy in detecting infected eyes, providing a rapid, non-invasive, and scalable diagnostic tool. This approach has the potential to support ophthalmologists in early screening and can be deployed in  GUI-based applications.