Performance Analysis of Feature Extraction Approach: Local Binary Pattern and Principal Component Analysis for Iris Recognition system

Many techniques have been proposed for the recognition of Iris. Most them are single resolution which results in poor performance. In this paper, feature extraction approaches like local binary pattern and principal component analysis assimilation has offered. For classification, Support Vector Machine used. This paper compares efficiency two popular methods Principal Component Analysis Local Binary Pattern using different iris databases CASIA UBIRIS. The models were tested 200 images. Statistical parameters F1 score Accuracy threshold values. Our method with accuracy 94 92%, is obtained UBIRIS data set respectively. Receiver Operating Characteristic Curve drawn Area under also calculated. experiment extended by varying dataset sizes. result shows that LBP achieves better performance both compared to PCA.