Combination of Physiological and Behavioral Biometric for Human Identification

Emdad Hossain; Girija Chetty

doi:10.1007/978-3-642-31537-4_30

Combination of Physiological and Behavioral Biometric for Human Identification

Emdad Hossain, Girija Chetty

Information Systems

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

1 Citation (Scopus)

Abstract

In this paper we propose a novel person-identification scheme based on gait biometric information in surveillance videos using simple PCA-LDA features, and RBF-MLP and SMO-SVM classifier. The experimental evaluation on resolution surveillance video images from a publicly available database [1] showed that the combined PCA-MLP and LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns.

Original language	English
Title of host publication	International Workshop on Machine Learning and Data Mining in Pattern Recognition
Subtitle of host publication	Lecture Notes in Artificial Intelligence
Editors	Petra Perner
Place of Publication	Berlin, Germany
Publisher	Springer
Pages	380-393
Number of pages	14
Volume	7376
ISBN (Electronic)	9783642315374
ISBN (Print)	9783642315367
DOIs	https://doi.org/10.1007/978-3-642-31537-4_30
Publication status	Published - 2012
Event	8th International Workshop on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012 - Berlin, Berlin, Germany Duration: 13 Jul 2012 → 20 Jul 2012

Conference

Conference	8th International Workshop on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012
Abbreviated title	MLDM 2012
Country/Territory	Germany
City	Berlin
Period	13/07/12 → 20/07/12

Access to Document

10.1007/978-3-642-31537-4_30

Cite this

@inproceedings{2abc4d95955d473d9475adc6b18d32b9,

title = "Combination of Physiological and Behavioral Biometric for Human Identification",

abstract = "In this paper we propose a novel person-identification scheme based on gait biometric information in surveillance videos using simple PCA-LDA features, and RBF-MLP and SMO-SVM classifier. The experimental evaluation on resolution surveillance video images from a publicly available database [1] showed that the combined PCA-MLP and LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns.",

keywords = "Multimodal, MLP, PCA, LDA, identification, SMO, J48",

author = "Emdad Hossain and Girija Chetty",

year = "2012",

doi = "10.1007/978-3-642-31537-4_30",

language = "English",

isbn = "9783642315367",

volume = "7376",

pages = "380--393",

editor = "Petra Perner",

booktitle = "International Workshop on Machine Learning and Data Mining in Pattern Recognition",

publisher = "Springer",

address = "Netherlands",

note = "8th International Workshop on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012, MLDM 2012 ; Conference date: 13-07-2012 Through 20-07-2012",

}

Hossain, E & Chetty, G 2012, Combination of Physiological and Behavioral Biometric for Human Identification. in P Perner (ed.), International Workshop on Machine Learning and Data Mining in Pattern Recognition: Lecture Notes in Artificial Intelligence. vol. 7376, Springer, Berlin, Germany, pp. 380-393, 8th International Workshop on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012, Berlin, Berlin, Germany, 13/07/12. https://doi.org/10.1007/978-3-642-31537-4_30

Combination of Physiological and Behavioral Biometric for Human Identification. / Hossain, Emdad; Chetty, Girija.
International Workshop on Machine Learning and Data Mining in Pattern Recognition: Lecture Notes in Artificial Intelligence. ed. / Petra Perner. Vol. 7376 Berlin, Germany: Springer, 2012. p. 380-393.

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

TY - GEN

T1 - Combination of Physiological and Behavioral Biometric for Human Identification

AU - Hossain, Emdad

AU - Chetty, Girija

PY - 2012

Y1 - 2012

N2 - In this paper we propose a novel person-identification scheme based on gait biometric information in surveillance videos using simple PCA-LDA features, and RBF-MLP and SMO-SVM classifier. The experimental evaluation on resolution surveillance video images from a publicly available database [1] showed that the combined PCA-MLP and LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns.

AB - In this paper we propose a novel person-identification scheme based on gait biometric information in surveillance videos using simple PCA-LDA features, and RBF-MLP and SMO-SVM classifier. The experimental evaluation on resolution surveillance video images from a publicly available database [1] showed that the combined PCA-MLP and LDA-MLP technique turns out to be a powerful method for capturing identity specific information from walking gait patterns.

KW - Multimodal

KW - MLP

KW - PCA

KW - LDA

KW - identification

KW - SMO

KW - J48

U2 - 10.1007/978-3-642-31537-4_30

DO - 10.1007/978-3-642-31537-4_30

M3 - Conference contribution

SN - 9783642315367

VL - 7376

SP - 380

EP - 393

BT - International Workshop on Machine Learning and Data Mining in Pattern Recognition

A2 - Perner, Petra

PB - Springer

CY - Berlin, Germany

T2 - 8th International Workshop on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012

Y2 - 13 July 2012 through 20 July 2012

ER -