IRIS RECOGNITION SYSTEM USING SUPERVISED AND UNSUPERVISED LEARNING TECHNIQUE

The iris recognition system is a reliable biometric identification method that utilizes the unique patterns of the human iris for accurate personal authentication. This project focuses on developing an iris recognition model that integrates both supervised and unsupervised learning techniques to improve accuracy and efficiency. The system involves key processes such as image acquisition, preprocessing, segmentation, feature extraction, and classification. Unsupervised learning methods like Principal Component Analysis (PCA) and K-Means clustering are used to reduce dimensionality and enhance feature representation, while supervised learning algorithms such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) are applied for precise classification and identification. By combining these techniques, the system achieves improved performance, adaptability, and robustness against variations in lighting and noise. The hybrid learning approach demonstrates the potential for building a more secure, intelligent, and efficient biometric recognition system suitable for modern authentication applications.