Multi-view gait recognition using enhanced gait energy image and radon transform techniques

Iman Mohammed Burhan, Md. Jan Nordin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Gait is an overall perceived biometric gimmick that is utilized to distinguish a human at a separation. Gait Recognition (GR) systems encounter several challenges, including viewing angles and translation variations. Hence, GR systems require the development of a robust gait representation model which is invariant in varying conditions. As such, this study presents a gait representation model for Multi-view Gait Recognition Systems (MvGRS) based on Gait Energy Image (GEI) and Radon Transform (RT) on human silhouettes to overcome the challenges in human recognition. In this regard, GEI is utilized for the description of gait features of binary silhouette images which are robust in multi-viewing and varied in appearances. Furthermore, the adoption of Radon Transform (RT) allows for the accommodation of gait representation model with RT features and silhouette alignment. This is to overcome the difficulties in geometrical transformation such as translation, scale and rotation. Consequently robust Principal Component Analysis (PCA) and Partial Least Square (PLS) approaches are accomplished in the reduction of these dimension feature vectors and feature selection. Finally, the recognition of gaits is based on similarity in measurements using Euclidean distance. The experiments were conducted on the public data set of CASIA. The findings from these experiments show that the results are better in comparison with the other methods. Thus, this indicates that the proposed method for gait recognition can outperform the existing methods in gait recognition.

Original languageEnglish
Pages (from-to)138-148
Number of pages11
JournalAsian Journal of Applied Sciences
Volume8
Issue number2
DOIs
Publication statusPublished - 2015

Fingerprint

Radon
Mathematical transformations
Binary images
Biometrics
Principal component analysis
Feature extraction
Experiments

ASJC Scopus subject areas

  • General

Cite this

Multi-view gait recognition using enhanced gait energy image and radon transform techniques. / Burhan, Iman Mohammed; Nordin, Md. Jan.

In: Asian Journal of Applied Sciences, Vol. 8, No. 2, 2015, p. 138-148.

Research output: Contribution to journalArticle

@article{684a7d78342f4dbd8fa7418edf8ed8ee,
title = "Multi-view gait recognition using enhanced gait energy image and radon transform techniques",
abstract = "Gait is an overall perceived biometric gimmick that is utilized to distinguish a human at a separation. Gait Recognition (GR) systems encounter several challenges, including viewing angles and translation variations. Hence, GR systems require the development of a robust gait representation model which is invariant in varying conditions. As such, this study presents a gait representation model for Multi-view Gait Recognition Systems (MvGRS) based on Gait Energy Image (GEI) and Radon Transform (RT) on human silhouettes to overcome the challenges in human recognition. In this regard, GEI is utilized for the description of gait features of binary silhouette images which are robust in multi-viewing and varied in appearances. Furthermore, the adoption of Radon Transform (RT) allows for the accommodation of gait representation model with RT features and silhouette alignment. This is to overcome the difficulties in geometrical transformation such as translation, scale and rotation. Consequently robust Principal Component Analysis (PCA) and Partial Least Square (PLS) approaches are accomplished in the reduction of these dimension feature vectors and feature selection. Finally, the recognition of gaits is based on similarity in measurements using Euclidean distance. The experiments were conducted on the public data set of CASIA. The findings from these experiments show that the results are better in comparison with the other methods. Thus, this indicates that the proposed method for gait recognition can outperform the existing methods in gait recognition.",
author = "Burhan, {Iman Mohammed} and Nordin, {Md. Jan}",
year = "2015",
doi = "10.3923/ajaps.2015.138.148",
language = "English",
volume = "8",
pages = "138--148",
journal = "Asian Journal of Applied Sciences",
issn = "1996-3343",
publisher = "Science Alert",
number = "2",

}

TY - JOUR

T1 - Multi-view gait recognition using enhanced gait energy image and radon transform techniques

AU - Burhan, Iman Mohammed

AU - Nordin, Md. Jan

PY - 2015

Y1 - 2015

N2 - Gait is an overall perceived biometric gimmick that is utilized to distinguish a human at a separation. Gait Recognition (GR) systems encounter several challenges, including viewing angles and translation variations. Hence, GR systems require the development of a robust gait representation model which is invariant in varying conditions. As such, this study presents a gait representation model for Multi-view Gait Recognition Systems (MvGRS) based on Gait Energy Image (GEI) and Radon Transform (RT) on human silhouettes to overcome the challenges in human recognition. In this regard, GEI is utilized for the description of gait features of binary silhouette images which are robust in multi-viewing and varied in appearances. Furthermore, the adoption of Radon Transform (RT) allows for the accommodation of gait representation model with RT features and silhouette alignment. This is to overcome the difficulties in geometrical transformation such as translation, scale and rotation. Consequently robust Principal Component Analysis (PCA) and Partial Least Square (PLS) approaches are accomplished in the reduction of these dimension feature vectors and feature selection. Finally, the recognition of gaits is based on similarity in measurements using Euclidean distance. The experiments were conducted on the public data set of CASIA. The findings from these experiments show that the results are better in comparison with the other methods. Thus, this indicates that the proposed method for gait recognition can outperform the existing methods in gait recognition.

AB - Gait is an overall perceived biometric gimmick that is utilized to distinguish a human at a separation. Gait Recognition (GR) systems encounter several challenges, including viewing angles and translation variations. Hence, GR systems require the development of a robust gait representation model which is invariant in varying conditions. As such, this study presents a gait representation model for Multi-view Gait Recognition Systems (MvGRS) based on Gait Energy Image (GEI) and Radon Transform (RT) on human silhouettes to overcome the challenges in human recognition. In this regard, GEI is utilized for the description of gait features of binary silhouette images which are robust in multi-viewing and varied in appearances. Furthermore, the adoption of Radon Transform (RT) allows for the accommodation of gait representation model with RT features and silhouette alignment. This is to overcome the difficulties in geometrical transformation such as translation, scale and rotation. Consequently robust Principal Component Analysis (PCA) and Partial Least Square (PLS) approaches are accomplished in the reduction of these dimension feature vectors and feature selection. Finally, the recognition of gaits is based on similarity in measurements using Euclidean distance. The experiments were conducted on the public data set of CASIA. The findings from these experiments show that the results are better in comparison with the other methods. Thus, this indicates that the proposed method for gait recognition can outperform the existing methods in gait recognition.

UR - http://www.scopus.com/inward/record.url?scp=84921919416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921919416&partnerID=8YFLogxK

U2 - 10.3923/ajaps.2015.138.148

DO - 10.3923/ajaps.2015.138.148

M3 - Article

VL - 8

SP - 138

EP - 148

JO - Asian Journal of Applied Sciences

JF - Asian Journal of Applied Sciences

SN - 1996-3343

IS - 2

ER -