Hybrid method for Gait recognition using SVM and Baysian Network

Ankit Gupta, P. W.C. Prasad, Abeer Alsadoon, Kamini Bajaj

Research output: Book chapter/Published conference paperConference paper

Abstract

The Gait recognition is the 2nd generation of biometric identification technology which aims to identify people at a distance by the way they walk. Due to the fact that there has been increasing research interest in the identification of an individual in access controlled environments such as the airports, banks and car parks, it has been observed that the effective human gait recognition plays a very important role in such video surveillance based applications. This paper proposes an effective Gait recognition method for automatic person recognition using SVM and Bayesian Network. In this method frames of videos are used as an input, these videos are live and are from the CASIA dataset. The background subtraction is done using Gait Pal and Pal Entropy and a Median Filter is also used to remove noise from the background. Feature selection is done using the Hanavan's model to reduce the computational cost during training and recognition. Support Vector Machine (SVM) and Bayesian Network are used for training and testing purpose. The experimental results show that the proposed approach has a very effective Correct Classification rate (CCR).
Original languageEnglish
Title of host publication2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages89-94
Number of pages6
ISBN (Electronic)9781479998869
DOIs
Publication statusPublished - 11 Apr 2016
Event8th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Etajima Community Center, Hiroshima, Japan
Duration: 06 Nov 201507 Nov 2015
http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/ (Conference website)

Conference

Conference8th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2015
CountryJapan
CityHiroshima
Period06/11/1507/11/15
Internet address

Fingerprint

Gait Recognition
Bayesian networks
Hybrid Method
Support vector machines
Support Vector Machine
Bayesian Networks
Median filters
Biometrics
Airports
Feature extraction
Median Filter
Background Subtraction
Entropy
Railroad cars
Video Surveillance
Gait
Walk
Feature Selection
Computational Cost
Person

Cite this

Gupta, A., Prasad, P. W. C., Alsadoon, A., & Bajaj, K. (2016). Hybrid method for Gait recognition using SVM and Baysian Network. In 2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings (pp. 89-94). [7449468] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IWCIA.2015.7449468
Gupta, Ankit ; Prasad, P. W.C. ; Alsadoon, Abeer ; Bajaj, Kamini. / Hybrid method for Gait recognition using SVM and Baysian Network. 2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 89-94
@inproceedings{ddb921ce6fa443fa89e5fde7ee4b0e27,
title = "Hybrid method for Gait recognition using SVM and Baysian Network",
abstract = "The Gait recognition is the 2nd generation of biometric identification technology which aims to identify people at a distance by the way they walk. Due to the fact that there has been increasing research interest in the identification of an individual in access controlled environments such as the airports, banks and car parks, it has been observed that the effective human gait recognition plays a very important role in such video surveillance based applications. This paper proposes an effective Gait recognition method for automatic person recognition using SVM and Bayesian Network. In this method frames of videos are used as an input, these videos are live and are from the CASIA dataset. The background subtraction is done using Gait Pal and Pal Entropy and a Median Filter is also used to remove noise from the background. Feature selection is done using the Hanavan's model to reduce the computational cost during training and recognition. Support Vector Machine (SVM) and Bayesian Network are used for training and testing purpose. The experimental results show that the proposed approach has a very effective Correct Classification rate (CCR).",
keywords = "Bayesian Network, Gait Pal and Pal Entropy, Gait recognition, Hanavan's Model, Support Vector Machine(SVM)",
author = "Ankit Gupta and Prasad, {P. W.C.} and Abeer Alsadoon and Kamini Bajaj",
year = "2016",
month = "4",
day = "11",
doi = "10.1109/IWCIA.2015.7449468",
language = "English",
pages = "89--94",
booktitle = "2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Gupta, A, Prasad, PWC, Alsadoon, A & Bajaj, K 2016, Hybrid method for Gait recognition using SVM and Baysian Network. in 2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings., 7449468, IEEE, Institute of Electrical and Electronics Engineers, pp. 89-94, 8th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2015, Hiroshima, Japan, 06/11/15. https://doi.org/10.1109/IWCIA.2015.7449468

Hybrid method for Gait recognition using SVM and Baysian Network. / Gupta, Ankit; Prasad, P. W.C.; Alsadoon, Abeer; Bajaj, Kamini.

2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 89-94 7449468.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Hybrid method for Gait recognition using SVM and Baysian Network

AU - Gupta, Ankit

AU - Prasad, P. W.C.

AU - Alsadoon, Abeer

AU - Bajaj, Kamini

PY - 2016/4/11

Y1 - 2016/4/11

N2 - The Gait recognition is the 2nd generation of biometric identification technology which aims to identify people at a distance by the way they walk. Due to the fact that there has been increasing research interest in the identification of an individual in access controlled environments such as the airports, banks and car parks, it has been observed that the effective human gait recognition plays a very important role in such video surveillance based applications. This paper proposes an effective Gait recognition method for automatic person recognition using SVM and Bayesian Network. In this method frames of videos are used as an input, these videos are live and are from the CASIA dataset. The background subtraction is done using Gait Pal and Pal Entropy and a Median Filter is also used to remove noise from the background. Feature selection is done using the Hanavan's model to reduce the computational cost during training and recognition. Support Vector Machine (SVM) and Bayesian Network are used for training and testing purpose. The experimental results show that the proposed approach has a very effective Correct Classification rate (CCR).

AB - The Gait recognition is the 2nd generation of biometric identification technology which aims to identify people at a distance by the way they walk. Due to the fact that there has been increasing research interest in the identification of an individual in access controlled environments such as the airports, banks and car parks, it has been observed that the effective human gait recognition plays a very important role in such video surveillance based applications. This paper proposes an effective Gait recognition method for automatic person recognition using SVM and Bayesian Network. In this method frames of videos are used as an input, these videos are live and are from the CASIA dataset. The background subtraction is done using Gait Pal and Pal Entropy and a Median Filter is also used to remove noise from the background. Feature selection is done using the Hanavan's model to reduce the computational cost during training and recognition. Support Vector Machine (SVM) and Bayesian Network are used for training and testing purpose. The experimental results show that the proposed approach has a very effective Correct Classification rate (CCR).

KW - Bayesian Network

KW - Gait Pal and Pal Entropy

KW - Gait recognition

KW - Hanavan's Model

KW - Support Vector Machine(SVM)

UR - http://www.scopus.com/inward/citedby.url?scp=84966661276&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7449445

UR - http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/files/IWICA2015TechnicalProgram.pdf

UR - http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/files/IWCIA2015_CFP.pdf

UR - http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/

U2 - 10.1109/IWCIA.2015.7449468

DO - 10.1109/IWCIA.2015.7449468

M3 - Conference paper

AN - SCOPUS:84966661276

SP - 89

EP - 94

BT - 2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Gupta A, Prasad PWC, Alsadoon A, Bajaj K. Hybrid method for Gait recognition using SVM and Baysian Network. In 2015 IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 89-94. 7449468 https://doi.org/10.1109/IWCIA.2015.7449468