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

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 hand-crafted features that ignores some additional features. For tackling problem described above, Convolution Neural Network (CNN) model inspired by Alex-net learns from ROI images classifies using fuzzy support vector machine is proposed. The output CNN fed as input Support machine. CNN's receptive field aids extracting most images, Fuzzy SVM results robust classification. experiments conducted on popular contactless datasets such IITD, POLYU2, Tongji, CASIA databases. Results demonstrate our approach outperformers several state-of-art techniques for recognition. Using this approach, we obtain 99.98% testing accuracy Tongji dataset 99.76 % POLYU-II datasets.