Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering
Sam Yin Yee
Universiti Malaysia Pahang, Kuantan, Malaysia
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Face Recognition Using Completed Local Ternary Pattern (CLTP) Texture Descriptor Taha H. Rassem; Nasrin M. Makbol; Sam Yin Yee
International Journal of Electrical and Computer Engineering (IJECE) Vol 7, No 3: June 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (414.165 KB) | DOI: 10.11591/ijece.v7i3.pp1594-1601

Abstract

Nowadays, face recognition becomes one of the important topics in the computer vision and image processing area. This is due to its importance where can be used in many applications. The main key in the face recognition is how to extract distinguishable features from the image to perform high recognition accuracy.  Local binary pattern (LBP) and many of its variants used as texture features in many of face recognition systems. Although LBP performed well in many fields, it is sensitive to noise, and different patterns of LBP may classify into the same class that reduces its discriminating property. Completed Local Ternary Pattern (CLTP) is one of the new proposed texture features to overcome the drawbacks of the LBP. The CLTP outperformed LBP and some of its variants in many fields such as texture, scene, and event image classification.  In this study, we study and investigate the performance of CLTP operator for face recognition task. The Japanese Female Facial Expression (JAFFE), and FEI face databases are used in the experiments. In the experimental results, CLTP outperformed some previous texture descriptors and achieves higher classification rate for face recognition task which has reached up 99.38% and 85.22% in JAFFE and FEI, respectively.
Co-Authors Nasrin M. Makbol Taha H. Rassem