Finger Vein Verification Using A Siamese Cnn
IET BIOMETRICS(2019)
摘要
Finger vein verification has received more attention recently due to its unique advantages. However, most existing algorithms rely on handcrafted features, making them less robust to finger rotation and offsets. To alleviate these problems, the authors propose a novel method to extract more discriminative features from finger vein images. First, facing the issue of insufficient training data, they adopt a heavy image augmentation strategy and develop a pretrained-weights based convolutional neural network (CNN). Second, focusing on the characteristics of finger vein verification, they construct a Siamese structure combining with a modified contrastive loss function for training the above CNN, which effectively improves the network's performance. Finally, considering the feasibility of deploying the above CNN on embedded devices, they construct a lightweight CNN with depthwise separable convolution and adopt a knowledge distillation method to learn the knowledge from the pretrained-weights based CNN, which makes it small but effective. The experimental results show that the size of the lightweight CNN shrinks to 1/6th of the pretrained-weights based CNN, while its equal error rates achieved in the MMCBNU_6000, FV-USM and SDUMLA-HMT datasets are 0.08, 0.11 and 0.75% respectively, which nearly stays the same with the pretrained-weights based CNN and surpasses state-of-the-art methods.
更多查看译文
关键词
vein recognition, feature extraction, learning (artificial intelligence), convolutional neural nets, finger vein verification, Siamese CNN, image quality deterioration, finger rotation, finger vein images, heavy image augmentation strategy, pretrained-weights based convolutional neural network, lightweight CNN, pretrained-weights based CNN, handcrafted features, finger offsets, discriminative feature extraction, insufficient training data, Siamese structure, metric learning, modified contrastive loss function, embedded devices, depthwise separable convolution, knowledge distillation method, equal error rates, SDUMLA-HMT datasets, FV-USM datasets, MMCBNU_6000 datasets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络