计算机技术与发展2018，Vol.28Issue(2)：200-204,5.DOI:10.3969/j.issn.1673-629X.2018.02.043
基于深度学习的指静脉识别研究
Research on Finger Vein Recognition Based on Deep Learning
摘要
Abstract
In this paper,we put forward a finger vein recognition algorithm based on deep learning.In the collection of finger vein image, sometimes the finger contour is blur due to the influence of illumination intensity.In order to obtain a clear vein image,morphological algo-rithm is used to extract the region of interest for the original image,and the Gaussian high pass filter is adopted to enhance it.An angle cor-rection algorithm is for eliminating the influence caused by the different degrees of finger rotation in the collection of finger vein image.Mo-reover,deep learning is performed well in image classification,especially the AlexNet in the ImageNet contest.Therefore,the neural network based on AlexNet is adopted to classify the finger vein image.In order to speed up the training,we modify the structure of the AlexNet net-work,including the size of the convolution kernel and the structure of the convolution layer,which lowers the network parameters,reduces network complexity,and accelerates the training of the network.The experiments show that using deep learning for classification of finger vein image has better effect.关键词
指静脉识别/形态学算法/角度修正算法/深度学习Key words
finger vein recognition/morphological algorithm/angle correction algorithm/deep learning分类
信息技术与安全科学引用本文复制引用
吴超,邵曦..基于深度学习的指静脉识别研究[J].计算机技术与发展,2018,28(2):200-204,5.基金项目
国家自然科学青年基金项目(61401227) （61401227）
