Principal component analysis and local binary patterns: A comparative study using different databases

Abstract

This paper compares the efficiency of two popular feature extraction methods Principal Component Analysis and Local Binary Pattern using two different iris databases CASIA and UBIRIS. For classification, Support Vector Machine has been used. The models were tested using 200 iris images. The Receiver Operating Characteristic Curve has been drawn and AUC was calculated. The result shows that LBP achieves better performance with both CASIA and UBIRIS databases compared to PCA. The experiment has been extended by varying the dataset sizes. The result has shown that LBP outperforms PCA with both CASIA and UBIRIS.