Face recognition with directional ternary pattern (DTP)

Md. Hasanul Kabir; Faisal Ahmed

doi:10.1117/12.2009559

14 March 2013 Face recognition with directional ternary pattern (DTP)

Md. Hasanul Kabir, Faisal Ahmed

Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 87687E (2013) https://doi.org/10.1117/12.2009559
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore

Abstract

This paper presents an effective and robust facial feature descriptor based on the directional ternary pattern (DTP) for face recognition. The DTP operator encodes the texture information of a local region by labeling the edge response values in all eight directions around a pixel with three different levels. The coding scheme exploits a threshold in order to differentiate between smooth and high-textured face regions while forming the ternary code. The location and occurrence information of the DTP micro-patterns within the facial image is then used as the feature descriptor. The effectiveness of the proposed method is evaluated with the FERET face image database using template matching (TM). Extensive experiments show the superiority of the DTP feature descriptor against some well-known local pattern-based feature representation methods.

Citation Download Citation

Md. Hasanul Kabir and Faisal Ahmed "Face recognition with directional ternary pattern (DTP)", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87687E (14 March 2013); https://doi.org/10.1117/12.2009559

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available