A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition

• DOI: 10.1007/s11633-020-1257-9
• Publication Date: 2020-12-30T03:02:42Z
• Authors: Wei Jia; Jian Gao; Wei Xia; Yang Zhao; Hai Min; Jing-Ting Lu
• Keywords: Palm print

Abstract Palmprint recognition and palm vein are two emerging biometrics technologies. In the past decades, many traditional methods have been proposed for palmprint recognition, achieved impressive results. However, research on deep learning-based is still very preliminary. this paper, in order to investigate problem of learning based 2D 3D in-depth, we conduct performance evaluation seventeen representative classic convolutional neural networks (CNNs) one database, five databases databases. A lot experiments carried out conditions different network structures, rates, numbers layers. We also conducted both separate data mode mixed mode. Experimental results show that these CNNs can achieve promising results, recently better. Particularly, among CNNs, i.e., EfficientNet achieves best accuracy. slightly worse than some methods.