Finger vein is located in the inner layer of finger skin and is not easy to change.Using finger vein for identity recog-nition and verification has become a research hotspot in the field of biometrics.The finger vein recognition based on CNN has large amount of parameters,large amount of calculation and long running time.To solve these problems,this paper proposes a finger vein recognition algorithm based on improved lightweight network(MobileNet).The improved network integrates particle swarm optimiza-tion(PSO)to optimize the parameters of MobileNet.Experimental results show that the recognition algorithm reduces the amount of parameters and operation time on the premise of maintaining high accuracy.
关键词
深度学习/指静脉识别/轻量级网络/粒子群算法
Key words
deep learning/finger vein recognition/MobileNet/PSO
维普
万方数据