Relaxed local ternary pattern for face recognition

Jianfeng Ren; Xudong Jiang; Junsong Yuan

doi:10.1109/ICIP.2013.6738759

Relaxed local ternary pattern for face recognition

Jianfeng Ren, Xudong Jiang, Junsong Yuan

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

56 Citations (Scopus)

Abstract

Local binary pattern (LBP) is sensitive to noise. Local ternary pattern (LTP) partially solves this problem by encoding the small pixel difference into a third state. The small pixel difference may be easily overwhelmed by noise. Thus, it is difficult to precisely determine its sign and magnitude. In this paper, we propose the concept of uncertain state to encode the small pixel difference. We do not care its sign and magnitude, and encode it as both 0 and 1 with equal probability. The proposed Relaxed LTP is tested on the CMU-PIE database, the extended Yale B database and the O2FN mobile face database. Superior performance is demonstrated compared with LBP and LTP.

Original language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages	3680-3684
Number of pages	5
DOIs	https://doi.org/10.1109/ICIP.2013.6738759
Publication status	Published - 2013
Externally published	Yes
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia Duration: 15 Sept 2013 → 18 Sept 2013

Publication series

Name	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Conference

Conference	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	15/09/13 → 18/09/13

Keywords

Face Recognition
Local Binary Pattern
Local Ternary Pattern
Relaxed LTP
Uncertain State

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2013.6738759

Cite this

@inproceedings{c5bfd7aaeabc486b9b1e1e4de1f04e9e,

title = "Relaxed local ternary pattern for face recognition",

abstract = "Local binary pattern (LBP) is sensitive to noise. Local ternary pattern (LTP) partially solves this problem by encoding the small pixel difference into a third state. The small pixel difference may be easily overwhelmed by noise. Thus, it is difficult to precisely determine its sign and magnitude. In this paper, we propose the concept of uncertain state to encode the small pixel difference. We do not care its sign and magnitude, and encode it as both 0 and 1 with equal probability. The proposed Relaxed LTP is tested on the CMU-PIE database, the extended Yale B database and the O2FN mobile face database. Superior performance is demonstrated compared with LBP and LTP.",

keywords = "Face Recognition, Local Binary Pattern, Local Ternary Pattern, Relaxed LTP, Uncertain State",

author = "Jianfeng Ren and Xudong Jiang and Junsong Yuan",

year = "2013",

doi = "10.1109/ICIP.2013.6738759",

language = "English",

isbn = "9781479923410",

series = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

pages = "3680--3684",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

}

Ren, J, Jiang, X & Yuan, J 2013, Relaxed local ternary pattern for face recognition. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738759, 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, pp. 3680-3684, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 15/09/13. https://doi.org/10.1109/ICIP.2013.6738759

Relaxed local ternary pattern for face recognition. / Ren, Jianfeng; Jiang, Xudong; Yuan, Junsong.
2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 3680-3684 6738759 (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Relaxed local ternary pattern for face recognition

AU - Ren, Jianfeng

AU - Jiang, Xudong

AU - Yuan, Junsong

PY - 2013

Y1 - 2013

N2 - Local binary pattern (LBP) is sensitive to noise. Local ternary pattern (LTP) partially solves this problem by encoding the small pixel difference into a third state. The small pixel difference may be easily overwhelmed by noise. Thus, it is difficult to precisely determine its sign and magnitude. In this paper, we propose the concept of uncertain state to encode the small pixel difference. We do not care its sign and magnitude, and encode it as both 0 and 1 with equal probability. The proposed Relaxed LTP is tested on the CMU-PIE database, the extended Yale B database and the O2FN mobile face database. Superior performance is demonstrated compared with LBP and LTP.

AB - Local binary pattern (LBP) is sensitive to noise. Local ternary pattern (LTP) partially solves this problem by encoding the small pixel difference into a third state. The small pixel difference may be easily overwhelmed by noise. Thus, it is difficult to precisely determine its sign and magnitude. In this paper, we propose the concept of uncertain state to encode the small pixel difference. We do not care its sign and magnitude, and encode it as both 0 and 1 with equal probability. The proposed Relaxed LTP is tested on the CMU-PIE database, the extended Yale B database and the O2FN mobile face database. Superior performance is demonstrated compared with LBP and LTP.

KW - Face Recognition

KW - Local Binary Pattern

KW - Local Ternary Pattern

KW - Relaxed LTP

KW - Uncertain State

UR - http://www.scopus.com/inward/record.url?scp=84897769474&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738759

DO - 10.1109/ICIP.2013.6738759

M3 - Conference contribution

AN - SCOPUS:84897769474

SN - 9781479923410

T3 - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

SP - 3680

EP - 3684

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Relaxed local ternary pattern for face recognition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this