Investigating the Use of Autoencoders for Gait-based Person Recognition

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 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 languageEnglish
Title of host publication2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages148-151
Number of pages4
ISBN (Electronic)9781538677537
ISBN (Print)9781538677544
DOIs
Publication statusPublished - 22 Nov 2018
Event2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018 - Edinburgh, United Kingdom
Duration: 6 Aug 20189 Aug 2018

Conference

Conference2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018
Country/TerritoryUnited Kingdom
CityEdinburgh
Period6/08/189/08/18

Fingerprint

Dive into the research topics of 'Investigating the Use of Autoencoders for Gait-based Person Recognition'. Together they form a unique fingerprint.

Cite this