Title | ||
---|---|---|
A novel finger vein verification system based on two-stream convolutional network learning. |
Abstract | ||
---|---|---|
Convolutional neural networks have been proven to have strong feature representation ability; however, they often require large training samples and high computation that are infeasible for real-time finger vein verification. To address this limitation, we propose a lightweight deep-learning framework for finger vein verification. First, we designed a lightweight two-channel network that has only three convolution layers for finger vein verification. Then, we extracted the mini-ROI from the original image to better solve the displacement problem based on the evaluation of the two-channel network. Finally, we present a two-stream network to integrate the original image and the mini-ROI that achieves results superior to the current state of the art on both the MMCBNU and SDUMLA databases. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.neucom.2018.02.042 | Neurocomputing |
Keywords | Field | DocType |
Finger vein verification,Deep learning,Metric network,Two-stream network | Pattern recognition,Convolution,Convolutional neural network,Artificial intelligence,Verification system,Mathematics,Computation | Journal |
Volume | ISSN | Citations |
290 | 0925-2312 | 8 |
PageRank | References | Authors |
0.46 | 17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuxun Fang | 1 | 25 | 2.74 |
Qiuxia Wu | 2 | 9 | 3.20 |
Wenxiong Kang | 3 | 38 | 6.66 |