Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features

Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features

Biometric identification systems have recently made exponential advancements in term of complexity and accuracy in recognition for security purposes and a variety of other application. In this paper, a Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeletal j...

Full description

Bibliographic Details
Published in:International Journal of Engineering and Technology(UAE)
Main Author: Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
Format: Article
Language:English
Published: Science Publishing Corporation Inc 2018
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054390444&doi=10.14419%2fijet.v7i4.11.20806&partnerID=40&md5=228e55a666d98781ca580243381ededa
id 2-s2.0-85054390444
spelling 2-s2.0-85054390444
Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
2018
International Journal of Engineering and Technology(UAE)
7
4
10.14419/ijet.v7i4.11.20806
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054390444&doi=10.14419%2fijet.v7i4.11.20806&partnerID=40&md5=228e55a666d98781ca580243381ededa
Biometric identification systems have recently made exponential advancements in term of complexity and accuracy in recognition for security purposes and a variety of other application. In this paper, a Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeletal joint data points is proposed for human identification. A total of 23 subjects were used for the experiments. The subjects were positioned 45 degrees (oblique view) from Kinect. A CNN based on the modified AlexNet structure was used to fit the different input data size. The results indicate that the training and testing accuracies were 100% and 69.6% respectively. © 2018 Authors.
Science Publishing Corporation Inc
2227524X
English
Article
All Open Access; Bronze Open Access
author Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
spellingShingle Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
author_facet Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
author_sort Guntor M.S.M.; Sahak R.; Zabidi A.; Tahir N.M.; Yassin I.M.; Rizman Z.I.; Baharom R.; Wahab N.A.
title Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
title_short Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
title_full Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
title_fullStr Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
title_full_unstemmed Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
title_sort Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeleton features
publishDate 2018
container_title International Journal of Engineering and Technology(UAE)
container_volume 7
container_issue 4
doi_str_mv 10.14419/ijet.v7i4.11.20806
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054390444&doi=10.14419%2fijet.v7i4.11.20806&partnerID=40&md5=228e55a666d98781ca580243381ededa
description Biometric identification systems have recently made exponential advancements in term of complexity and accuracy in recognition for security purposes and a variety of other application. In this paper, a Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeletal joint data points is proposed for human identification. A total of 23 subjects were used for the experiments. The subjects were positioned 45 degrees (oblique view) from Kinect. A CNN based on the modified AlexNet structure was used to fit the different input data size. The results indicate that the training and testing accuracies were 100% and 69.6% respectively. © 2018 Authors.
publisher Science Publishing Corporation Inc
issn 2227524X
language English
format Article
accesstype All Open Access; Bronze Open Access
record_format scopus
collection Scopus
_version_ 1809677907575963648

Similar Items