Multimodal face-gait fusion for biometric person authentication

Emdad Hossain, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

7 Citations (Scopus)

Abstract

In this paper we propose a novel multimodal fusion approach based on PCA-LDA processing for person identification from low resolution surveillance video with cues extracted from gait and face biometrics. The experimental evaluation of the proposed scheme on a publicly available database [2] showed that the combined PCA-LDA face and gait when fused in either hierarchical or holistic fusion, can lead to powerful identity verification that can capture the inherent multimodality in walking gait patterns and ascertain the identity from low resolution surveillance videos.

Original languageEnglish
Title of host publicationProceedings - 2011 IFIP 9th International Conference on Embedded and Ubiquitous Computing, EUC 2011
PublisherIEEE
Pages332-337
Number of pages6
ISBN (Print)9781457718229, 9780769545523
DOIs
Publication statusPublished - 2011
Event2011 IFIP 9th International Conference on Embedded and Ubiquitous Computing, EUC 2011 - Melbourne, VIC, Australia
Duration: 24 Oct 201126 Oct 2011

Conference

Conference2011 IFIP 9th International Conference on Embedded and Ubiquitous Computing, EUC 2011
CountryAustralia
CityMelbourne, VIC
Period24/10/1126/10/11

    Fingerprint

Cite this

Hossain, E., & Chetty, G. (2011). Multimodal face-gait fusion for biometric person authentication. In Proceedings - 2011 IFIP 9th International Conference on Embedded and Ubiquitous Computing, EUC 2011 (pp. 332-337). [6104546] IEEE. https://doi.org/10.1109/EUC.2011.52