Abstract
This study affords the method of using advance correlation filters in human posture recognition task. Two type of correlation filters were implemented and their efficacy evaluated. The correlation filters under consideration are Minimum Average Correlation Energy (MACE) and Unconstrained Minimum Average Correlation Energy (UMACE). Initial results prove that correlation filters offer significant potential used in posture recognition task with UMACE outperforming the MACE filter. In this research, both filters were subjected to a challenging task to recognize human posture without any restriction on the gender, clothing and posture variations. The UMACE filter performs remarkably well with an average accuracy of 89% compared to MACE filter which attained 42%.
| Original language | English |
|---|---|
| Pages (from-to) | 2947-2956 |
| Number of pages | 10 |
| Journal | Journal of Applied Sciences |
| Volume | 7 |
| Issue number | 20 |
| DOIs | |
| Publication status | Published - 2007 Oct 15 |
All Science Journal Classification (ASJC) codes
- General
Cite this
}
On the use of advanced correlation filters for human posture recognition. / Tahir, Nooritawati Md; Hussain, Aini; Samad, Salina Abdul; Husain, Hafizah; Jin, Andrew Teoh Beng.
In: Journal of Applied Sciences, Vol. 7, No. 20, 15.10.2007, p. 2947-2956.Research output: Contribution to journal › Article
TY - JOUR
T1 - On the use of advanced correlation filters for human posture recognition
AU - Tahir, Nooritawati Md
AU - Hussain, Aini
AU - Samad, Salina Abdul
AU - Husain, Hafizah
AU - Jin, Andrew Teoh Beng
PY - 2007/10/15
Y1 - 2007/10/15
N2 - This study affords the method of using advance correlation filters in human posture recognition task. Two type of correlation filters were implemented and their efficacy evaluated. The correlation filters under consideration are Minimum Average Correlation Energy (MACE) and Unconstrained Minimum Average Correlation Energy (UMACE). Initial results prove that correlation filters offer significant potential used in posture recognition task with UMACE outperforming the MACE filter. In this research, both filters were subjected to a challenging task to recognize human posture without any restriction on the gender, clothing and posture variations. The UMACE filter performs remarkably well with an average accuracy of 89% compared to MACE filter which attained 42%.
AB - This study affords the method of using advance correlation filters in human posture recognition task. Two type of correlation filters were implemented and their efficacy evaluated. The correlation filters under consideration are Minimum Average Correlation Energy (MACE) and Unconstrained Minimum Average Correlation Energy (UMACE). Initial results prove that correlation filters offer significant potential used in posture recognition task with UMACE outperforming the MACE filter. In this research, both filters were subjected to a challenging task to recognize human posture without any restriction on the gender, clothing and posture variations. The UMACE filter performs remarkably well with an average accuracy of 89% compared to MACE filter which attained 42%.
UR - http://www.scopus.com/inward/record.url?scp=36849090801&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=36849090801&partnerID=8YFLogxK
U2 - 10.3923/jas.2007.2947.2956
DO - 10.3923/jas.2007.2947.2956
M3 - Article
AN - SCOPUS:36849090801
VL - 7
SP - 2947
EP - 2956
JO - Journal of Applied Sciences
JF - Journal of Applied Sciences
SN - 1812-5654
IS - 20
ER -