Neural network ensemble with probabilistic fusion and its application to gait recognition

Heesung Lee, Sungjun Hong, Euntai Kim

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

The recognition of a person from his (or her) gait is a relatively new and promising research direction in biometrics since it is noninvasive and human friendly. Gait recognition, however, has the weakness that it is not reliable compared with other biometrics. To increase reliability, we applied a neural network ensemble with probabilistic fusion to the gait recognition problem. To improve recognition accuracy, we define belief as the posterior probability of the pattern and combine the component neural networks of the ensemble based on the belief. Experiments are performed with the NLPR and SOTON databases, and the effectiveness of the proposed method for gait recognition is demonstrated.

Original languageEnglish
Pages (from-to)1557-1564
Number of pages8
JournalNeurocomputing
Volume72
Issue number7-9
DOIs
Publication statusPublished - 2009 Mar 1

Fingerprint

Biometrics
Gait
Fusion reactions
Neural networks
Experiments
Databases
Research

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

Lee, Heesung ; Hong, Sungjun ; Kim, Euntai. / Neural network ensemble with probabilistic fusion and its application to gait recognition. In: Neurocomputing. 2009 ; Vol. 72, No. 7-9. pp. 1557-1564.
@article{4f442ffd35ae456099e2d194d16d1a5b,
title = "Neural network ensemble with probabilistic fusion and its application to gait recognition",
abstract = "The recognition of a person from his (or her) gait is a relatively new and promising research direction in biometrics since it is noninvasive and human friendly. Gait recognition, however, has the weakness that it is not reliable compared with other biometrics. To increase reliability, we applied a neural network ensemble with probabilistic fusion to the gait recognition problem. To improve recognition accuracy, we define belief as the posterior probability of the pattern and combine the component neural networks of the ensemble based on the belief. Experiments are performed with the NLPR and SOTON databases, and the effectiveness of the proposed method for gait recognition is demonstrated.",
author = "Heesung Lee and Sungjun Hong and Euntai Kim",
year = "2009",
month = "3",
day = "1",
doi = "10.1016/j.neucom.2008.09.009",
language = "English",
volume = "72",
pages = "1557--1564",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "7-9",

}

Neural network ensemble with probabilistic fusion and its application to gait recognition. / Lee, Heesung; Hong, Sungjun; Kim, Euntai.

In: Neurocomputing, Vol. 72, No. 7-9, 01.03.2009, p. 1557-1564.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network ensemble with probabilistic fusion and its application to gait recognition

AU - Lee, Heesung

AU - Hong, Sungjun

AU - Kim, Euntai

PY - 2009/3/1

Y1 - 2009/3/1

N2 - The recognition of a person from his (or her) gait is a relatively new and promising research direction in biometrics since it is noninvasive and human friendly. Gait recognition, however, has the weakness that it is not reliable compared with other biometrics. To increase reliability, we applied a neural network ensemble with probabilistic fusion to the gait recognition problem. To improve recognition accuracy, we define belief as the posterior probability of the pattern and combine the component neural networks of the ensemble based on the belief. Experiments are performed with the NLPR and SOTON databases, and the effectiveness of the proposed method for gait recognition is demonstrated.

AB - The recognition of a person from his (or her) gait is a relatively new and promising research direction in biometrics since it is noninvasive and human friendly. Gait recognition, however, has the weakness that it is not reliable compared with other biometrics. To increase reliability, we applied a neural network ensemble with probabilistic fusion to the gait recognition problem. To improve recognition accuracy, we define belief as the posterior probability of the pattern and combine the component neural networks of the ensemble based on the belief. Experiments are performed with the NLPR and SOTON databases, and the effectiveness of the proposed method for gait recognition is demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=61849145792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849145792&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2008.09.009

DO - 10.1016/j.neucom.2008.09.009

M3 - Article

VL - 72

SP - 1557

EP - 1564

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 7-9

ER -