Investigating the Use of Autoencoders for Gait-based Person Recognition

Ismahane Cheheb; Noor Al-Maadeed; Somaya Al-Madeed; Ahmed Bouridane

doi:10.1109/AHS.2018.8541447

Investigating the Use of Autoencoders for Gait-based Person Recognition

Ismahane Cheheb, Noor Al-Maadeed, Somaya Al-Madeed, Ahmed Bouridane

Computer and Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

In recent years, gait has been growing as a biometric for person recognition at a distance. However, factors such as view angles and carrying conditions often make this task challenging. This paper proposes a solution to this problem by modelling gait sequences using Gait Energy Images and then using sparse autoencoders to extract their features for recognition under different view angles. Experiments were carried out on the challenging CASIA B dataset, resulting in outstanding accuracy rates.

Original language	English
Title of host publication	2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	148-151
Number of pages	4
ISBN (Electronic)	9781538677537
ISBN (Print)	9781538677544
DOIs	https://doi.org/10.1109/AHS.2018.8541447
Publication status	Published - 22 Nov 2018
Event	2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018 - Edinburgh, United Kingdom Duration: 6 Aug 2018 → 9 Aug 2018

Conference

Conference	2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018
Country/Territory	United Kingdom
City	Edinburgh
Period	6/08/18 → 9/08/18

Keywords

Autoencoder
Gait
GEI

Access to Document

10.1109/AHS.2018.8541447

Cite this

@inproceedings{230173cc0b154826ac8b5f9873b04f8c,

title = "Investigating the Use of Autoencoders for Gait-based Person Recognition",

abstract = "In recent years, gait has been growing as a biometric for person recognition at a distance. However, factors such as view angles and carrying conditions often make this task challenging. This paper proposes a solution to this problem by modelling gait sequences using Gait Energy Images and then using sparse autoencoders to extract their features for recognition under different view angles. Experiments were carried out on the challenging CASIA B dataset, resulting in outstanding accuracy rates.",

keywords = "Autoencoder, Gait, GEI",

author = "Ismahane Cheheb and Noor Al-Maadeed and Somaya Al-Madeed and Ahmed Bouridane",

year = "2018",

month = nov,

day = "22",

doi = "10.1109/AHS.2018.8541447",

language = "English",

isbn = "9781538677544",

pages = "148--151",

booktitle = "2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018 ; Conference date: 06-08-2018 Through 09-08-2018",

}

Cheheb, I, Al-Maadeed, N, Al-Madeed, S & Bouridane, A 2018, Investigating the Use of Autoencoders for Gait-based Person Recognition. in 2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018. Institute of Electrical and Electronics Engineers Inc., pp. 148-151, 2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018, Edinburgh, United Kingdom, 6/08/18. https://doi.org/10.1109/AHS.2018.8541447

Investigating the Use of Autoencoders for Gait-based Person Recognition. / Cheheb, Ismahane; Al-Maadeed, Noor; Al-Madeed, Somaya et al.
2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 148-151.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Investigating the Use of Autoencoders for Gait-based Person Recognition

AU - Cheheb, Ismahane

AU - Al-Maadeed, Noor

AU - Al-Madeed, Somaya

AU - Bouridane, Ahmed

PY - 2018/11/22

Y1 - 2018/11/22

N2 - In recent years, gait has been growing as a biometric for person recognition at a distance. However, factors such as view angles and carrying conditions often make this task challenging. This paper proposes a solution to this problem by modelling gait sequences using Gait Energy Images and then using sparse autoencoders to extract their features for recognition under different view angles. Experiments were carried out on the challenging CASIA B dataset, resulting in outstanding accuracy rates.

AB - In recent years, gait has been growing as a biometric for person recognition at a distance. However, factors such as view angles and carrying conditions often make this task challenging. This paper proposes a solution to this problem by modelling gait sequences using Gait Energy Images and then using sparse autoencoders to extract their features for recognition under different view angles. Experiments were carried out on the challenging CASIA B dataset, resulting in outstanding accuracy rates.

KW - Autoencoder

KW - Gait

KW - GEI

U2 - 10.1109/AHS.2018.8541447

DO - 10.1109/AHS.2018.8541447

M3 - Conference contribution

AN - SCOPUS:85059964724

SN - 9781538677544

SP - 148

EP - 151

BT - 2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018

Y2 - 6 August 2018 through 9 August 2018

ER -

Investigating the Use of Autoencoders for Gait-based Person Recognition

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this