Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition

Emdad Hossain; Girija CHETTY

doi:10.1007/978-3-642-42042-9_89

Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition

Emdad Hossain, Girija CHETTY

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

20 Citations (Scopus)

Abstract

In this paper we propose a novel multimodal feature learning technique based on deep learning for gait biometric based human-identification scheme from surveillance videos. Experimental evaluation of proposed learning features based on novel deep learning and standard (PCA/LDA) features in combination with classifier techniques (NN/MLP/SVM/SMO) on different datasets from two gait databases (the publicly available CASIA multiview multispectral database, and the UCMG multiview database), show a significant improvement in recognition accuracies with proposed fused deep learning features.

Original language	English
Title of host publication	20th International Conference on Neural Information Processing (ICONIP 2013)
Subtitle of host publication	Lecture Notes in Computer Science
Editors	Minho Lee, Akira Hirose, Zeng-Guang, Hou, Rhee Man Kil
Place of Publication	Germany
Publisher	Springer
Pages	721-728
Number of pages	8
Volume	8227
ISBN (Electronic)	9783642420429
ISBN (Print)	9783642420412
DOIs	https://doi.org/10.1007/978-3-642-42042-9_89
Publication status	Published - 2013
Event	20th International Conference on Neural Information Processing (ICONIP 2013) - Daegu, Daegu, Korea, Republic of Duration: 3 Nov 2013 → 7 Nov 2013

Conference

Conference	20th International Conference on Neural Information Processing (ICONIP 2013)
Abbreviated title	ICONIP 2013
Country/Territory	Korea, Republic of
City	Daegu
Period	3/11/13 → 7/11/13

Access to Document

10.1007/978-3-642-42042-9_89

Cite this

@inproceedings{08b4c0d74c204a41b7b3bd899dee0fed,

title = "Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition",

abstract = "In this paper we propose a novel multimodal feature learning technique based on deep learning for gait biometric based human-identification scheme from surveillance videos. Experimental evaluation of proposed learning features based on novel deep learning and standard (PCA/LDA) features in combination with classifier techniques (NN/MLP/SVM/SMO) on different datasets from two gait databases (the publicly available CASIA multiview multispectral database, and the UCMG multiview database), show a significant improvement in recognition accuracies with proposed fused deep learning features.",

keywords = "Multimodal, Deep learning, Fusion, Multiview, Gait, vPCA, Identification",

author = "Emdad Hossain and Girija CHETTY",

year = "2013",

doi = "10.1007/978-3-642-42042-9_89",

language = "English",

isbn = "9783642420412",

volume = "8227",

pages = "721--728",

editor = "Minho Lee and Akira Hirose and Zeng-Guang and Hou and Kil, {Rhee Man}",

booktitle = "20th International Conference on Neural Information Processing (ICONIP 2013)",

publisher = "Springer",

address = "Netherlands",

note = "20th International Conference on Neural Information Processing (ICONIP 2013), ICONIP 2013 ; Conference date: 03-11-2013 Through 07-11-2013",

}

Hossain, E & CHETTY, G 2013, Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition. in M Lee, A Hirose, Zeng-Guang, Hou & RM Kil (eds), 20th International Conference on Neural Information Processing (ICONIP 2013): Lecture Notes in Computer Science. vol. 8227, Springer, Germany, pp. 721-728, 20th International Conference on Neural Information Processing (ICONIP 2013), Daegu, Korea, Republic of, 3/11/13. https://doi.org/10.1007/978-3-642-42042-9_89

Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition. / Hossain, Emdad; CHETTY, Girija.
20th International Conference on Neural Information Processing (ICONIP 2013): Lecture Notes in Computer Science. ed. / Minho Lee; Akira Hirose; Zeng-Guang; Hou; Rhee Man Kil. Vol. 8227 Germany: Springer, 2013. p. 721-728.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition

AU - Hossain, Emdad

AU - CHETTY, Girija

PY - 2013

Y1 - 2013

N2 - In this paper we propose a novel multimodal feature learning technique based on deep learning for gait biometric based human-identification scheme from surveillance videos. Experimental evaluation of proposed learning features based on novel deep learning and standard (PCA/LDA) features in combination with classifier techniques (NN/MLP/SVM/SMO) on different datasets from two gait databases (the publicly available CASIA multiview multispectral database, and the UCMG multiview database), show a significant improvement in recognition accuracies with proposed fused deep learning features.

AB - In this paper we propose a novel multimodal feature learning technique based on deep learning for gait biometric based human-identification scheme from surveillance videos. Experimental evaluation of proposed learning features based on novel deep learning and standard (PCA/LDA) features in combination with classifier techniques (NN/MLP/SVM/SMO) on different datasets from two gait databases (the publicly available CASIA multiview multispectral database, and the UCMG multiview database), show a significant improvement in recognition accuracies with proposed fused deep learning features.

KW - Multimodal

KW - Deep learning

KW - Fusion

KW - Multiview

KW - Gait

KW - vPCA

KW - Identification

UR - https://link.springer.com/chapter/10.1007%2F978-3-642-42042-9_89

U2 - 10.1007/978-3-642-42042-9_89

DO - 10.1007/978-3-642-42042-9_89

M3 - Conference contribution

SN - 9783642420412

VL - 8227

SP - 721

EP - 728

BT - 20th International Conference on Neural Information Processing (ICONIP 2013)

A2 - Lee, Minho

A2 - Hirose, Akira

A2 - Zeng-Guang, null

A2 - Hou, null

A2 - Kil, Rhee Man

PB - Springer

CY - Germany

T2 - 20th International Conference on Neural Information Processing (ICONIP 2013)

Y2 - 3 November 2013 through 7 November 2013

ER -

Multimodal Feature Learning for Gait Biometric Base Human Identity Recognition

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this