Automation in Detection of Color Vision Deficiency Using Machine Learning

Color Vision Deficiency (CVD) limits individuals ability to distinguish colors accurately, leading to challenges in safety-critical fields such as driving, military operations, and various professional roles. Despite its prevalence, undiagnosed CVD poses significant safety risks and impacts productivity. Traditional diagnostic methods, while effective, often fail to engage users, particularly children, resulting in incomplete or inaccurate results. This project introduces an automated system for detecting color blindness that is simple, engaging, and user-friendly. Utilizing machine learning, the system classifies the type of CVD-Deuteranopia, Protanopia, or normal vision—based on responses to Ishihara test plates. To enhance engagement, the system incorporates interactive 3D models to dynamically present the plates, making the diagnostic process enjoyable, especially for children. Its compact and scalable design ensures versatility, making it suitable for use in schools, clinics, and even at home. By combining automation and interactivity, this system improves diagnostic accuracy, raises awareness, and fosters safer, more inclusive environments.