A new gait recognition system based on hierarchical fair competition-based parallel genetic algorithm and selective neural network ensemble

Heesung Lee, Heejin Lee, Euntai Kim

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The recognition of a person from his or her gait has been a recent focus in computer vision because of its unique advantages such as being non-invasive and human friendly. However, gait recognition is not as reliable an identifier as other biometrics. In this paper, we applied a hierarchical fair competition-based parallel genetic algorithm and a neural network ensemble to the gait recognition problem. A diverse set of potential neural networks are generated to increase the reliability of the gait recognition, not only the best ones. Furthermore, a set of component neural networks is selected to build a gait recognition system such that generalization errors are minimized and negative correlation is maximized. Experiments are carried out with the NLPR and SOTON gait databases and the effectiveness of the proposed method for gait recognition is demonstrated and compared to previous methods.

Original languageEnglish
Pages (from-to)202-207
Number of pages6
JournalInternational Journal of Control, Automation and Systems
Volume12
Issue number1
DOIs
Publication statusPublished - 2014 Feb 1

Fingerprint

Parallel algorithms
Genetic algorithms
Neural networks
Biometrics
Computer vision
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications

Cite this

@article{829eab45fd0141ff9d591bf3b3626db6,
title = "A new gait recognition system based on hierarchical fair competition-based parallel genetic algorithm and selective neural network ensemble",
abstract = "The recognition of a person from his or her gait has been a recent focus in computer vision because of its unique advantages such as being non-invasive and human friendly. However, gait recognition is not as reliable an identifier as other biometrics. In this paper, we applied a hierarchical fair competition-based parallel genetic algorithm and a neural network ensemble to the gait recognition problem. A diverse set of potential neural networks are generated to increase the reliability of the gait recognition, not only the best ones. Furthermore, a set of component neural networks is selected to build a gait recognition system such that generalization errors are minimized and negative correlation is maximized. Experiments are carried out with the NLPR and SOTON gait databases and the effectiveness of the proposed method for gait recognition is demonstrated and compared to previous methods.",
author = "Heesung Lee and Heejin Lee and Euntai Kim",
year = "2014",
month = "2",
day = "1",
doi = "10.1007/s12555-012-0154-6",
language = "English",
volume = "12",
pages = "202--207",
journal = "International Journal of Control, Automation and Systems",
issn = "1598-6446",
publisher = "Institute of Control, Robotics and Systems",
number = "1",

}

TY - JOUR

T1 - A new gait recognition system based on hierarchical fair competition-based parallel genetic algorithm and selective neural network ensemble

AU - Lee, Heesung

AU - Lee, Heejin

AU - Kim, Euntai

PY - 2014/2/1

Y1 - 2014/2/1

N2 - The recognition of a person from his or her gait has been a recent focus in computer vision because of its unique advantages such as being non-invasive and human friendly. However, gait recognition is not as reliable an identifier as other biometrics. In this paper, we applied a hierarchical fair competition-based parallel genetic algorithm and a neural network ensemble to the gait recognition problem. A diverse set of potential neural networks are generated to increase the reliability of the gait recognition, not only the best ones. Furthermore, a set of component neural networks is selected to build a gait recognition system such that generalization errors are minimized and negative correlation is maximized. Experiments are carried out with the NLPR and SOTON gait databases and the effectiveness of the proposed method for gait recognition is demonstrated and compared to previous methods.

AB - The recognition of a person from his or her gait has been a recent focus in computer vision because of its unique advantages such as being non-invasive and human friendly. However, gait recognition is not as reliable an identifier as other biometrics. In this paper, we applied a hierarchical fair competition-based parallel genetic algorithm and a neural network ensemble to the gait recognition problem. A diverse set of potential neural networks are generated to increase the reliability of the gait recognition, not only the best ones. Furthermore, a set of component neural networks is selected to build a gait recognition system such that generalization errors are minimized and negative correlation is maximized. Experiments are carried out with the NLPR and SOTON gait databases and the effectiveness of the proposed method for gait recognition is demonstrated and compared to previous methods.

UR - http://www.scopus.com/inward/record.url?scp=84896787566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896787566&partnerID=8YFLogxK

U2 - 10.1007/s12555-012-0154-6

DO - 10.1007/s12555-012-0154-6

M3 - Article

VL - 12

SP - 202

EP - 207

JO - International Journal of Control, Automation and Systems

JF - International Journal of Control, Automation and Systems

SN - 1598-6446

IS - 1

ER -