A Finger Knuckle Print Classification System Using SVM for Different LBP Variants

Finger knuckle print is one of the most important biometric traits and plays a vital role in a secure identification system. In this paper, performance evaluation of local binary pattern (LBP) and its variants center symmetric local binary pattern (CS-LBP) and median local binary pattern (MLBP) are investigated. After feature extraction, a support vector machine (SVM) with the linear kernel is used for the performance evaluation of two different datasets named the Poly-U FKP dataset and the USM-FKP dataset. The experimental results show that CS-LBP performs better for the USM-FKP dataset with an accuracy of 86.2% which demonstrates the potential of the FKP classification system.