Person identification from human walking sequences using affine moment invariants

Yumi Iwashita, Ryo Kurazume

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

18 Citations (Scopus)

Abstract

This paper proposes a new person identification method using physiological and behavioral biometrics. Various person recognition systems have been proposed so far, and one of the recently introduced human characteristics for the person identification is gait. Although the shape of one's body has not been considered much as a characteristic, it is closely related to gait and it is difficult to disassociate them. So, the proposed technique introduces a new hybrid biometric, combining body shape (physiological) and gait (behavioral). The new biometric is the full spatio-temporal volume carved by a person who walks. In addition to this biometric, we extract unique biometrics in individuals by the following way: creating the average image from the spatio-temporal volume and forming the new spatio-temporal volume from differential images which are created by subtracting an average image from original images. Affine moment invariants are derived from these biometrics, and classified by a support vector machine. We used the leave-one-out cross validation technique to estimate the correct classification rate of 94 %.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Robotics and Automation, ICRA '09
Pages436-441
Number of pages6
DOIs
Publication statusPublished - Nov 2 2009
Event2009 IEEE International Conference on Robotics and Automation, ICRA '09 - Kobe, Japan
Duration: May 12 2009May 17 2009

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Other

Other2009 IEEE International Conference on Robotics and Automation, ICRA '09
CountryJapan
CityKobe
Period5/12/095/17/09

Fingerprint

Biometrics
Support vector machines

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Iwashita, Y., & Kurazume, R. (2009). Person identification from human walking sequences using affine moment invariants. In 2009 IEEE International Conference on Robotics and Automation, ICRA '09 (pp. 436-441). [5152485] (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ROBOT.2009.5152485

Person identification from human walking sequences using affine moment invariants. / Iwashita, Yumi; Kurazume, Ryo.

2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. p. 436-441 5152485 (Proceedings - IEEE International Conference on Robotics and Automation).

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

Iwashita, Y & Kurazume, R 2009, Person identification from human walking sequences using affine moment invariants. in 2009 IEEE International Conference on Robotics and Automation, ICRA '09., 5152485, Proceedings - IEEE International Conference on Robotics and Automation, pp. 436-441, 2009 IEEE International Conference on Robotics and Automation, ICRA '09, Kobe, Japan, 5/12/09. https://doi.org/10.1109/ROBOT.2009.5152485
Iwashita Y, Kurazume R. Person identification from human walking sequences using affine moment invariants. In 2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. p. 436-441. 5152485. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ROBOT.2009.5152485
Iwashita, Yumi ; Kurazume, Ryo. / Person identification from human walking sequences using affine moment invariants. 2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. pp. 436-441 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{d010a8a4da924d28887951f41dbe3c34,
title = "Person identification from human walking sequences using affine moment invariants",
abstract = "This paper proposes a new person identification method using physiological and behavioral biometrics. Various person recognition systems have been proposed so far, and one of the recently introduced human characteristics for the person identification is gait. Although the shape of one's body has not been considered much as a characteristic, it is closely related to gait and it is difficult to disassociate them. So, the proposed technique introduces a new hybrid biometric, combining body shape (physiological) and gait (behavioral). The new biometric is the full spatio-temporal volume carved by a person who walks. In addition to this biometric, we extract unique biometrics in individuals by the following way: creating the average image from the spatio-temporal volume and forming the new spatio-temporal volume from differential images which are created by subtracting an average image from original images. Affine moment invariants are derived from these biometrics, and classified by a support vector machine. We used the leave-one-out cross validation technique to estimate the correct classification rate of 94 {\%}.",
author = "Yumi Iwashita and Ryo Kurazume",
year = "2009",
month = "11",
day = "2",
doi = "10.1109/ROBOT.2009.5152485",
language = "English",
isbn = "9781424427895",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
pages = "436--441",
booktitle = "2009 IEEE International Conference on Robotics and Automation, ICRA '09",

}

TY - GEN

T1 - Person identification from human walking sequences using affine moment invariants

AU - Iwashita, Yumi

AU - Kurazume, Ryo

PY - 2009/11/2

Y1 - 2009/11/2

N2 - This paper proposes a new person identification method using physiological and behavioral biometrics. Various person recognition systems have been proposed so far, and one of the recently introduced human characteristics for the person identification is gait. Although the shape of one's body has not been considered much as a characteristic, it is closely related to gait and it is difficult to disassociate them. So, the proposed technique introduces a new hybrid biometric, combining body shape (physiological) and gait (behavioral). The new biometric is the full spatio-temporal volume carved by a person who walks. In addition to this biometric, we extract unique biometrics in individuals by the following way: creating the average image from the spatio-temporal volume and forming the new spatio-temporal volume from differential images which are created by subtracting an average image from original images. Affine moment invariants are derived from these biometrics, and classified by a support vector machine. We used the leave-one-out cross validation technique to estimate the correct classification rate of 94 %.

AB - This paper proposes a new person identification method using physiological and behavioral biometrics. Various person recognition systems have been proposed so far, and one of the recently introduced human characteristics for the person identification is gait. Although the shape of one's body has not been considered much as a characteristic, it is closely related to gait and it is difficult to disassociate them. So, the proposed technique introduces a new hybrid biometric, combining body shape (physiological) and gait (behavioral). The new biometric is the full spatio-temporal volume carved by a person who walks. In addition to this biometric, we extract unique biometrics in individuals by the following way: creating the average image from the spatio-temporal volume and forming the new spatio-temporal volume from differential images which are created by subtracting an average image from original images. Affine moment invariants are derived from these biometrics, and classified by a support vector machine. We used the leave-one-out cross validation technique to estimate the correct classification rate of 94 %.

UR - http://www.scopus.com/inward/record.url?scp=70350352773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350352773&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2009.5152485

DO - 10.1109/ROBOT.2009.5152485

M3 - Conference contribution

AN - SCOPUS:70350352773

SN - 9781424427895

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 436

EP - 441

BT - 2009 IEEE International Conference on Robotics and Automation, ICRA '09

ER -