Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

Yuxiang Guo; Cheng Peng; Chun Pong Lau; Rama Chellappa

doi:10.1109/FG57933.2023.10042572

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

Yuxiang Guo^*, Cheng Peng^*, Chun Pong Lau, Rama Chellappa

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

10 Citations (Scopus)

Abstract

Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern contributes to robust identification performance over a large range of viewing angles. Extensive experimental results on the CASIA-B dataset demonstrate that the proposed method outperforms state-of-the-art recognition systems. We also provide experimental results using the newly collected BRIAR dataset. © 2023 IEEE

Original language	English
Title of host publication	2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	9798350345445
ISBN (Print)	979-8-3503-4545-2
DOIs	https://doi.org/10.1109/FG57933.2023.10042572
Publication status	Published - 2023
Externally published	Yes
Event	17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023) - Waikoloa Beach Marriott Resort, Waikoloa, United States Duration: 5 Jan 2023 → 8 Jan 2023 https://fg2023.ieee-biometrics.org/

Publication series

Name	IEEE International Conference on Automatic Face and Gesture Recognition, FG

Conference

Conference	17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023)
Country/Territory	United States
City	Waikoloa
Period	5/01/23 → 8/01/23
Internet address	https://fg2023.ieee-biometrics.org/

Funding

VI. ACKNOWLEDGEMENT This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via [2022-21102100005]. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ODNI, IARPA, or the U.S. Government. The US. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.

Access Output

10.1109/FG57933.2023.10042572

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{d732d696233c448c993beed7563975e5,

title = "Multi-Modal Human Authentication Using Silhouettes, Gait and RGB",

abstract = "Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern contributes to robust identification performance over a large range of viewing angles. Extensive experimental results on the CASIA-B dataset demonstrate that the proposed method outperforms state-of-the-art recognition systems. We also provide experimental results using the newly collected BRIAR dataset. {\textcopyright} 2023 IEEE",

author = "Yuxiang Guo and Cheng Peng and Lau, {Chun Pong} and Rama Chellappa",

year = "2023",

doi = "10.1109/FG57933.2023.10042572",

language = "English",

isbn = "979-8-3503-4545-2",

series = "IEEE International Conference on Automatic Face and Gesture Recognition, FG",

publisher = "IEEE",

booktitle = "2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)",

address = "United States",

note = "17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023) ; Conference date: 05-01-2023 Through 08-01-2023",

url = "https://fg2023.ieee-biometrics.org/",

}

Guo, Y, Peng, C, Lau, CP & Chellappa, R 2023, Multi-Modal Human Authentication Using Silhouettes, Gait and RGB. in 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG). IEEE International Conference on Automatic Face and Gesture Recognition, FG, IEEE, 17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023), Waikoloa, United States, 5/01/23. https://doi.org/10.1109/FG57933.2023.10042572

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB. / Guo, Yuxiang; Peng, Cheng; Lau, Chun Pong et al.
2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG). IEEE, 2023. (IEEE International Conference on Automatic Face and Gesture Recognition, FG).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

AU - Guo, Yuxiang

AU - Peng, Cheng

AU - Lau, Chun Pong

AU - Chellappa, Rama

PY - 2023

Y1 - 2023

N2 - Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern contributes to robust identification performance over a large range of viewing angles. Extensive experimental results on the CASIA-B dataset demonstrate that the proposed method outperforms state-of-the-art recognition systems. We also provide experimental results using the newly collected BRIAR dataset. © 2023 IEEE

AB - Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern contributes to robust identification performance over a large range of viewing angles. Extensive experimental results on the CASIA-B dataset demonstrate that the proposed method outperforms state-of-the-art recognition systems. We also provide experimental results using the newly collected BRIAR dataset. © 2023 IEEE

UR - http://www.scopus.com/inward/record.url?scp=85149298658&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85149298658&origin=recordpage

U2 - 10.1109/FG57933.2023.10042572

DO - 10.1109/FG57933.2023.10042572

M3 - RGC 32 - Refereed conference paper (with host publication)

AN - SCOPUS:85149298658

SN - 979-8-3503-4545-2

T3 - IEEE International Conference on Automatic Face and Gesture Recognition, FG

BT - 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)

PB - IEEE

T2 - 17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023)

Y2 - 5 January 2023 through 8 January 2023

ER -

Multi-Modal Human Authentication Using Silhouettes, Gait and RGB

Abstract

Publication series

Conference

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this