Different Dimension Issues in Deep Feature Space for Finger-Vein Recognition

Yiqi Zhong, Jiahui Li, Tingting Chai, Shitala Prasad, Zhaoxin Zhang

Abstract: Hand-crafted approaches were the dominating solutions and recently, more convolutional neural network (CNN)-based methods have been proposed for finger-vein recognition. However, the previous deep learning methods usually designed the network architecture with increasing layers and parameters, which incurs device memory issues and processing speed issues. Although many researchers have devoted to design image enhancement algorithms to improve the recognition performance of hand-crafted methods, it is interesting to investigate whether deep learning method can achieve satisfactory performance without image enhancement. This paper focuses on two different dimension issues: lightweight CNN design and the impact of image enhancement on deep learning methods. The experimental results demonstrate that the proposed method LFVRN is comparable or superior to the prior competition winners. In addition, image enhancement is validated not inevitable for the proposed lightweight CNN model LFVRN.