VISIONID: ENHANCING IRIS RECOGNITION ACCURACY WITH MACHINE LEARNING

Abstract

Iris recognition has become one of the most reliable biometric authentication methods due to its uniqueness, stability, and resistance to forgery. However, achieving high accuracy remains challenging in the presence of noise, variations in lighting, occlusions, and image quality issues. This study explores the integration of advanced machine learning (ML) techniques to improve the accuracy and robustness of iris recognition systems. By employing feature extraction methods, dimensionality reduction, and classification algorithms, the proposed approach enhances pattern recognition and minimizes false acceptance and rejection rates. Experimental evaluations demonstrate that ML-based models outperform conventional methods, delivering significant improvements in recognition accuracy and computational efficiency. The research underscores the potential of machine learning as a transformative tool for developing nextgeneration biometric systems, contributing to enhanced security, reliability, and user convenience in real-world applications.