UMP Institutional Repository

Face Recognition Using Completed Local Ternary Pattern (CLTP) Texture Descriptor

Rassem, Taha H. and Makbol, Nasrin M. and Sam, Yin Yee (2017) Face Recognition Using Completed Local Ternary Pattern (CLTP) Texture Descriptor. International Journal of Electrical and Computer Engineering (IJECE), 7 (3). pp. 1594-1601. ISSN 2088-8708

This is the latest version of this item.

[img]
Preview
PDF
7528-7674-1-PB.pdf
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (414kB) | Preview

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.

Item Type: Article
Uncontrolled Keywords: Face r Fecognition Completed; local binary pattern (CLBP); Completed local ternary pattern (CLTP); Face dataset; Image classification
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Dr. Taha Hussein Alaaldeen Rassem
Date Deposited: 12 Oct 2017 08:27
Last Modified: 20 Mar 2018 04:22
URI: http://umpir.ump.edu.my/id/eprint/18514
Download Statistic: View Download Statistics

Available Versions of this Item

  • Face Recognition Using Completed Local Ternary Pattern (CLTP) Texture Descriptor. (deposited 12 Oct 2017 08:27) [Currently Displayed]

Actions (login required)

View Item View Item