Fast frontal view gait authentication based on the statistical registration and human gait modeling

Kosuke Okusa, Toshinari Kamakura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. To demonstrate the effectiveness of our method, we conducted experiment, assessing the proposed method for frontal view human gait authentication. We apply K-nearestneighbor classifier, using the estimated parameters, to perform the human gait authentication, and present results from an experiment involving 120 subjects. As a result, our method shows high recognition rate and low calculation cost.

Original languageEnglish
Title of host publicationProceedings of the World Congress on Engineering 2013, WCE 2013
Pages274-279
Number of pages6
Publication statusPublished - Nov 25 2013
Externally publishedYes
Event2013 World Congress on Engineering, WCE 2013 - London, United Kingdom
Duration: Jul 3 2013Jul 5 2013

Publication series

NameLecture Notes in Engineering and Computer Science
Volume1 LNECS
ISSN (Print)2078-0958

Other

Other2013 World Congress on Engineering, WCE 2013
CountryUnited Kingdom
CityLondon
Period7/3/137/5/13

Fingerprint

Authentication
Classifiers
Experiments
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)

Cite this

Okusa, K., & Kamakura, T. (2013). Fast frontal view gait authentication based on the statistical registration and human gait modeling. In Proceedings of the World Congress on Engineering 2013, WCE 2013 (pp. 274-279). (Lecture Notes in Engineering and Computer Science; Vol. 1 LNECS).

Fast frontal view gait authentication based on the statistical registration and human gait modeling. / Okusa, Kosuke; Kamakura, Toshinari.

Proceedings of the World Congress on Engineering 2013, WCE 2013. 2013. p. 274-279 (Lecture Notes in Engineering and Computer Science; Vol. 1 LNECS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okusa, K & Kamakura, T 2013, Fast frontal view gait authentication based on the statistical registration and human gait modeling. in Proceedings of the World Congress on Engineering 2013, WCE 2013. Lecture Notes in Engineering and Computer Science, vol. 1 LNECS, pp. 274-279, 2013 World Congress on Engineering, WCE 2013, London, United Kingdom, 7/3/13.
Okusa K, Kamakura T. Fast frontal view gait authentication based on the statistical registration and human gait modeling. In Proceedings of the World Congress on Engineering 2013, WCE 2013. 2013. p. 274-279. (Lecture Notes in Engineering and Computer Science).
Okusa, Kosuke ; Kamakura, Toshinari. / Fast frontal view gait authentication based on the statistical registration and human gait modeling. Proceedings of the World Congress on Engineering 2013, WCE 2013. 2013. pp. 274-279 (Lecture Notes in Engineering and Computer Science).
@inproceedings{7bd94fef80104cadb0a27b69e2c00860,
title = "Fast frontal view gait authentication based on the statistical registration and human gait modeling",
abstract = "We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. To demonstrate the effectiveness of our method, we conducted experiment, assessing the proposed method for frontal view human gait authentication. We apply K-nearestneighbor classifier, using the estimated parameters, to perform the human gait authentication, and present results from an experiment involving 120 subjects. As a result, our method shows high recognition rate and low calculation cost.",
author = "Kosuke Okusa and Toshinari Kamakura",
year = "2013",
month = "11",
day = "25",
language = "English",
isbn = "9789881925107",
series = "Lecture Notes in Engineering and Computer Science",
pages = "274--279",
booktitle = "Proceedings of the World Congress on Engineering 2013, WCE 2013",

}

TY - GEN

T1 - Fast frontal view gait authentication based on the statistical registration and human gait modeling

AU - Okusa, Kosuke

AU - Kamakura, Toshinari

PY - 2013/11/25

Y1 - 2013/11/25

N2 - We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. To demonstrate the effectiveness of our method, we conducted experiment, assessing the proposed method for frontal view human gait authentication. We apply K-nearestneighbor classifier, using the estimated parameters, to perform the human gait authentication, and present results from an experiment involving 120 subjects. As a result, our method shows high recognition rate and low calculation cost.

AB - We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. To demonstrate the effectiveness of our method, we conducted experiment, assessing the proposed method for frontal view human gait authentication. We apply K-nearestneighbor classifier, using the estimated parameters, to perform the human gait authentication, and present results from an experiment involving 120 subjects. As a result, our method shows high recognition rate and low calculation cost.

UR - http://www.scopus.com/inward/record.url?scp=84887936860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887936860&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84887936860

SN - 9789881925107

T3 - Lecture Notes in Engineering and Computer Science

SP - 274

EP - 279

BT - Proceedings of the World Congress on Engineering 2013, WCE 2013

ER -