Gait recognition system using decision-level fusion

Byungyun Lee, Sungjun Hong, Heesung Lee, Euntai Kim

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

15 Citations (Scopus)

Abstract

Gait recognition has recently attracted increasing interest from the biometric society. In this paper, we present a gait recognition system based on the fusion of multiple gait cycles using a new gait representation. First, a gait sequence is automatically partitioned into multiple gait cycles by finding the local minima of width signal. After gait cycle partitioning, we extract a new gait feature called motion contour image (MCI) that captures the contour of the binary silhouette image of a walking individual. Finally, for human identification, the outputs of nearest neighbor classifiers are fused at a decision level based on majority voting. Our proposed system is tested on the CASIA gait dataset A. Experimental results show that the proposed system is better than or equal to previous works in terms of correct classification rate.

Original languageEnglish
Title of host publicationProceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010
Pages313-316
Number of pages4
DOIs
Publication statusPublished - 2010 Sep 1
Event5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010 - Taichung, Taiwan, Province of China
Duration: 2010 Jun 152010 Jun 17

Publication series

NameProceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

Other

Other5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010
CountryTaiwan, Province of China
CityTaichung
Period10/6/1510/6/17

Fingerprint

Binary images
Biometrics
Classifiers
Fusion reactions

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Lee, B., Hong, S., Lee, H., & Kim, E. (2010). Gait recognition system using decision-level fusion. In Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010 (pp. 313-316). [5516856] (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010). https://doi.org/10.1109/ICIEA.2010.5516856
Lee, Byungyun ; Hong, Sungjun ; Lee, Heesung ; Kim, Euntai. / Gait recognition system using decision-level fusion. Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. pp. 313-316 (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010).
@inproceedings{1810bfa2d93544128c65dd265edd044c,
title = "Gait recognition system using decision-level fusion",
abstract = "Gait recognition has recently attracted increasing interest from the biometric society. In this paper, we present a gait recognition system based on the fusion of multiple gait cycles using a new gait representation. First, a gait sequence is automatically partitioned into multiple gait cycles by finding the local minima of width signal. After gait cycle partitioning, we extract a new gait feature called motion contour image (MCI) that captures the contour of the binary silhouette image of a walking individual. Finally, for human identification, the outputs of nearest neighbor classifiers are fused at a decision level based on majority voting. Our proposed system is tested on the CASIA gait dataset A. Experimental results show that the proposed system is better than or equal to previous works in terms of correct classification rate.",
author = "Byungyun Lee and Sungjun Hong and Heesung Lee and Euntai Kim",
year = "2010",
month = "9",
day = "1",
doi = "10.1109/ICIEA.2010.5516856",
language = "English",
isbn = "9781424450466",
series = "Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010",
pages = "313--316",
booktitle = "Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010",

}

Lee, B, Hong, S, Lee, H & Kim, E 2010, Gait recognition system using decision-level fusion. in Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010., 5516856, Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010, pp. 313-316, 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010, Taichung, Taiwan, Province of China, 10/6/15. https://doi.org/10.1109/ICIEA.2010.5516856

Gait recognition system using decision-level fusion. / Lee, Byungyun; Hong, Sungjun; Lee, Heesung; Kim, Euntai.

Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. p. 313-316 5516856 (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010).

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

TY - GEN

T1 - Gait recognition system using decision-level fusion

AU - Lee, Byungyun

AU - Hong, Sungjun

AU - Lee, Heesung

AU - Kim, Euntai

PY - 2010/9/1

Y1 - 2010/9/1

N2 - Gait recognition has recently attracted increasing interest from the biometric society. In this paper, we present a gait recognition system based on the fusion of multiple gait cycles using a new gait representation. First, a gait sequence is automatically partitioned into multiple gait cycles by finding the local minima of width signal. After gait cycle partitioning, we extract a new gait feature called motion contour image (MCI) that captures the contour of the binary silhouette image of a walking individual. Finally, for human identification, the outputs of nearest neighbor classifiers are fused at a decision level based on majority voting. Our proposed system is tested on the CASIA gait dataset A. Experimental results show that the proposed system is better than or equal to previous works in terms of correct classification rate.

AB - Gait recognition has recently attracted increasing interest from the biometric society. In this paper, we present a gait recognition system based on the fusion of multiple gait cycles using a new gait representation. First, a gait sequence is automatically partitioned into multiple gait cycles by finding the local minima of width signal. After gait cycle partitioning, we extract a new gait feature called motion contour image (MCI) that captures the contour of the binary silhouette image of a walking individual. Finally, for human identification, the outputs of nearest neighbor classifiers are fused at a decision level based on majority voting. Our proposed system is tested on the CASIA gait dataset A. Experimental results show that the proposed system is better than or equal to previous works in terms of correct classification rate.

UR - http://www.scopus.com/inward/record.url?scp=77956024838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956024838&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2010.5516856

DO - 10.1109/ICIEA.2010.5516856

M3 - Conference contribution

SN - 9781424450466

T3 - Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

SP - 313

EP - 316

BT - Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

ER -

Lee B, Hong S, Lee H, Kim E. Gait recognition system using decision-level fusion. In Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. p. 313-316. 5516856. (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010). https://doi.org/10.1109/ICIEA.2010.5516856