Innovative Computerized Approach for Accurate Color Blindness Detection

Abstract

A simple computerized method for the testing of color blindness (color vision deficiency, CVD) to enhance diagnostic accuracy as well as accessibility has been presented in this study. Ishi-hara plates and Farnsworth D-15 are traditional tests that require manual interpretation and may be prone to human error. The proposed system relies on contrast-based image processing, chromaticity contrast analysis, and machine learning models (convolutional neural networks (CNN) and support vector machines (SVM)) to classify such different types of color blindness with 95.4% accuracy. It transforms the image to multicolor spaces such as HSV, CIE-LAB, and YCbCr for enhanced perceptual uniformity and functions on digital screens without requiring special hardware. This system has a real-time adaptation that changes test parameters based on user responses to increase color differentiation. In contrast to existing techniques, this lightweight and cost-effective method does not consume high computational power or external sensors. In the future, augmented reality (AR) real-world color correction and cloud-based diagnosis for large-scale accessibility will be developed as an efficient, automated, and widespread color blindness testing solution.