File(s) under permanent embargo
Learning optimised representations for view-invariant gait recognition
conference contribution
posted on 2017-01-01, 00:00 authored by N Jia, V Sanchez, Chang-Tsun LiChang-Tsun LiGait recognition can be performed without subject cooperation under harsh conditions, thus it is an important tool in forensic gait analysis, security control, and other commercial applications. One critical issue that prevents gait recognition systems from being widely accepted is the performance drop when the camera viewpoint varies between the registered templates and the query data. In this paper, we explore the potential of combining feature optimisers and representations learned by convolutional neural networks (CNN) to achieve efficient view-invariant gait recognition. The experimental results indicate that CNN learns highly discriminative representations across moderate view variations, and these representations can be further improved using view-invariant feature selectors, achieving a high matching accuracy across views.
History
Event
IEEE Biometrics Council. Conference (2017 : Denver, Colo.)Series
IEEE Biometrics Council ConferencePagination
774 - 780Publisher
Institute of Electrical and Electronics EngineersLocation
Denver, Colo.Place of publication
Piscataway, N.J.Publisher DOI
Start date
2017-10-01End date
2017-10-04ISBN-13
9781538611241Language
engPublication classification
E Conference publication; E1.1 Full written paper - refereedCopyright notice
2017, IEEEEditor/Contributor(s)
[Unknown]Title of proceedings
IJCB 2017 : Proceedings of the 2017 International Joint Conference on BiometricsUsage metrics
Categories
Keywords
camerascomputational modelinggait recognitionprobessolid modelingtrainingScience & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Theory & MethodsEngineering, Electrical & ElectronicComputer ScienceEngineeringInformation SystemsArtificial Intelligence and Image ProcessingDistributed Computing
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC