An efficient gait recognition based on a selective neural network ensemble

Heesung Lee, Sungjun Hong, Euntai Kim

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

The neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. Generally, the ensemble shows better generalization performance than a single neural network. In this article, a selective neural network ensemble is applied to gait recognition. The proposed method selects some neural network based on the minimization of generalization error. Since the selection rule is directly incorporated into the cost function, we can obtain adequate component networks to constitute an ensemble. Experiments are performed with the NLPR database to show the performance of the proposed algorithm.

Original languageEnglish
Pages (from-to)237-241
Number of pages5
JournalInternational Journal of Imaging Systems and Technology
Volume18
Issue number4
DOIs
Publication statusPublished - 2008 Nov 10

Fingerprint

Neural networks
Network components
Cost functions
Experiments

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Software
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{1f60f10e888749d3ad480455b966be66,
title = "An efficient gait recognition based on a selective neural network ensemble",
abstract = "The neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. Generally, the ensemble shows better generalization performance than a single neural network. In this article, a selective neural network ensemble is applied to gait recognition. The proposed method selects some neural network based on the minimization of generalization error. Since the selection rule is directly incorporated into the cost function, we can obtain adequate component networks to constitute an ensemble. Experiments are performed with the NLPR database to show the performance of the proposed algorithm.",
author = "Heesung Lee and Sungjun Hong and Euntai Kim",
year = "2008",
month = "11",
day = "10",
doi = "10.1002/ima.20136",
language = "English",
volume = "18",
pages = "237--241",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

An efficient gait recognition based on a selective neural network ensemble. / Lee, Heesung; Hong, Sungjun; Kim, Euntai.

In: International Journal of Imaging Systems and Technology, Vol. 18, No. 4, 10.11.2008, p. 237-241.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient gait recognition based on a selective neural network ensemble

AU - Lee, Heesung

AU - Hong, Sungjun

AU - Kim, Euntai

PY - 2008/11/10

Y1 - 2008/11/10

N2 - The neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. Generally, the ensemble shows better generalization performance than a single neural network. In this article, a selective neural network ensemble is applied to gait recognition. The proposed method selects some neural network based on the minimization of generalization error. Since the selection rule is directly incorporated into the cost function, we can obtain adequate component networks to constitute an ensemble. Experiments are performed with the NLPR database to show the performance of the proposed algorithm.

AB - The neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. Generally, the ensemble shows better generalization performance than a single neural network. In this article, a selective neural network ensemble is applied to gait recognition. The proposed method selects some neural network based on the minimization of generalization error. Since the selection rule is directly incorporated into the cost function, we can obtain adequate component networks to constitute an ensemble. Experiments are performed with the NLPR database to show the performance of the proposed algorithm.

UR - http://www.scopus.com/inward/record.url?scp=55349141814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55349141814&partnerID=8YFLogxK

U2 - 10.1002/ima.20136

DO - 10.1002/ima.20136

M3 - Article

VL - 18

SP - 237

EP - 241

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 4

ER -