Palm Vein Recognition Based on Convolutional Neural Network

Convolutional neural networks (CNNs) were popular in ImageNet large scale visual recognition competition (ILSVRC 2012) because of their identification ability and computational efficiency. This paper proposes a palm vein method based on CNN. The four main steps are image acquisition, preprocessing, feature extraction, matching. To reduce the processing images, using CNN is proposed. deep learning network. Palm images acquired near-infrared light, under which veins hand relatively prominent. obtain good image, many previous methods used preprocessing to further enhance before extraction find matches for comparison. In recent years, CNNs have been shown great advantages performed well classification. early-stage processing, classify recognize images. AlexNet VGG depth trained extract features. rates by VGG-19, VGG-16, 98.5%, 97.5%, 96%, respectively.