Abstract
Gait recognition as a biometric attribute has the capability to be recognized in monitoring systems. In this paper, a method based on joint angle estimation of body motion for gait recognition is proposed. The representation of gait feature for the motion angles of upper and lower of body part is investigated and joint angle is calculated using Fourier, radon and Gabor features. Based on the joint angles estimation, we build a histogram of the feature individually. In the measurement stage of distance, χ2 function is used to measure the similarity between these histograms. After that, a classifier is built to implement the stage of classification. Experiments were tested on CASIA (B) Database to demonstrate that proposed method can attain a high-quality recognition performance.
| Original language | English |
|---|---|
| Pages (from-to) | 277-284 |
| Number of pages | 8 |
| Journal | Journal of Theoretical and Applied Information Technology |
| Volume | 81 |
| Issue number | 2 |
| Publication status | Published - 1 Nov 2015 |
Fingerprint
Keywords
- Gait recognition
- Joint angle
- Silhouette
- Skeletonization
- SVM
ASJC Scopus subject areas
- Computer Science(all)
- Theoretical Computer Science
Cite this
An automatic human gait recognition system based on joint angle estimation on silhouette images. / Saadoon, Ali; Nordin, Md. Jan.
In: Journal of Theoretical and Applied Information Technology, Vol. 81, No. 2, 01.11.2015, p. 277-284.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - An automatic human gait recognition system based on joint angle estimation on silhouette images
AU - Saadoon, Ali
AU - Nordin, Md. Jan
PY - 2015/11/1
Y1 - 2015/11/1
N2 - Gait recognition as a biometric attribute has the capability to be recognized in monitoring systems. In this paper, a method based on joint angle estimation of body motion for gait recognition is proposed. The representation of gait feature for the motion angles of upper and lower of body part is investigated and joint angle is calculated using Fourier, radon and Gabor features. Based on the joint angles estimation, we build a histogram of the feature individually. In the measurement stage of distance, χ2 function is used to measure the similarity between these histograms. After that, a classifier is built to implement the stage of classification. Experiments were tested on CASIA (B) Database to demonstrate that proposed method can attain a high-quality recognition performance.
AB - Gait recognition as a biometric attribute has the capability to be recognized in monitoring systems. In this paper, a method based on joint angle estimation of body motion for gait recognition is proposed. The representation of gait feature for the motion angles of upper and lower of body part is investigated and joint angle is calculated using Fourier, radon and Gabor features. Based on the joint angles estimation, we build a histogram of the feature individually. In the measurement stage of distance, χ2 function is used to measure the similarity between these histograms. After that, a classifier is built to implement the stage of classification. Experiments were tested on CASIA (B) Database to demonstrate that proposed method can attain a high-quality recognition performance.
KW - Gait recognition
KW - Joint angle
KW - Silhouette
KW - Skeletonization
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=84947607008&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84947607008&partnerID=8YFLogxK
M3 - Article
VL - 81
SP - 277
EP - 284
JO - Journal of Theoretical and Applied Information Technology
JF - Journal of Theoretical and Applied Information Technology
SN - 1992-8645
IS - 2
ER -