A probabilistic image-weighting scheme for robust silhouette-based gait recognition

Heesung Lee, Jeonghyun Baek, Euntai Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representationmethod by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.

Original languageEnglish
Pages (from-to)1399-1419
Number of pages21
JournalMultimedia Tools and Applications
Volume70
Issue number3
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Biometrics
Support vector machines
Degradation
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{55bd9ab9847d45abbb2c233ee6ac48f6,
title = "A probabilistic image-weighting scheme for robust silhouette-based gait recognition",
abstract = "Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representationmethod by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.",
author = "Heesung Lee and Jeonghyun Baek and Euntai Kim",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s11042-012-1163-4",
language = "English",
volume = "70",
pages = "1399--1419",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "3",

}

A probabilistic image-weighting scheme for robust silhouette-based gait recognition. / Lee, Heesung; Baek, Jeonghyun; Kim, Euntai.

In: Multimedia Tools and Applications, Vol. 70, No. 3, 01.01.2014, p. 1399-1419.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A probabilistic image-weighting scheme for robust silhouette-based gait recognition

AU - Lee, Heesung

AU - Baek, Jeonghyun

AU - Kim, Euntai

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representationmethod by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.

AB - Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representationmethod by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.

UR - http://www.scopus.com/inward/record.url?scp=84905571117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905571117&partnerID=8YFLogxK

U2 - 10.1007/s11042-012-1163-4

DO - 10.1007/s11042-012-1163-4

M3 - Article

VL - 70

SP - 1399

EP - 1419

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 3

ER -