Deep learning approach for Touchless Palmprint Recognition based on Alexnet and Fuzzy Support Vector Machine

Abstract

Due to stable and discriminative features, palmprint-based biometrics has been gaining popularity in recent years. Most of the traditional palmprint recognition systems are designed with a group of hand-crafted features that ignores some additional features. For tackling the problem described above, a Convolution Neural Network (CNN) model inspired by Alex-net that learns the features from the ROI images and classifies using a fuzzy support vector machine is proposed. The output of the CNN is fed as input to the fuzzy Support vector machine. The CNN's receptive field aids in extracting the most discriminative features from the palmprint images, and Fuzzy SVM results in a robust classification. The experiments are conducted on popular contactless datasets such as IITD, POLYU2, Tongji, and CASIA databases. Results demonstrate our approach outperformers several state-of-art techniques for palmprint recognition. Using this approach, we obtain 99.98% testing accuracy for the Tongji dataset and 99.76 % for the POLYU-II datasets.