Finger-vein presentation attack detection using depthwise separable convolution neural network
作者：
Highlights：
• A new presentation attack detection (PAD) method for FV biometric systems.
• An efficient DSC-LSVM method was applied to detect presentation attacks.
• Data limitation, Complexity and unavailability of lightweight model problem were fixed.
• The proposed deep learning model is effective in dealing with real-time scenarios.
• Extensive experiments and detailed comparative studies were presented.
摘要
•A new presentation attack detection (PAD) method for FV biometric systems.•An efficient DSC-LSVM method was applied to detect presentation attacks.•Data limitation, Complexity and unavailability of lightweight model problem were fixed.•The proposed deep learning model is effective in dealing with real-time scenarios.•Extensive experiments and detailed comparative studies were presented.
论文关键词：Biometric,Finger-vein presentation attack,Finger-vein recognition,Depthwise separable convolutional neural network,Support vector machine
论文评审过程：Received 24 December 2021, Revised 15 February 2022, Accepted 26 February 2022, Available online 7 March 2022, Version of Record 18 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116786
