Indexed by:
Abstract:
步态识别是新兴的生物特征识别技术,旨在基于行走姿态识别行人的身份。基于深度学习的步态识别方法已经被陆续提出。本文提出将密集连接卷积神经网络(Densenet)应用于步态特征提取,在CASIA-B步态数据集上与现有基于卷积神经网络的步态识别方法进行对比实验,并取得较高的识别准确率。
Keyword:
Reprint 's Address:
Email:
Version:
Source :
网络安全技术与应用
ISSN: 1009-6833
CN: 11-4522/TP
Year: 2019
Issue: 11
Page: 46-47
Cited Count:
WoS CC Cited Count: 0
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 2
Affiliated Colleges: