Face recognition with enhanced local gabor binary pattern from human fixations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Performance of automatic face recognition algorithm has increased considerably over the past decades. However, face recognition under changes in lighting conditions remains a challenging issue for computers. In this paper, we propose a novel face recognition algorithm inspired by information taken from human fixation patterns. We augment a LGBP (Local Gabor Binary Pattern) algorithm - a well-known face recognition algorithm - to allocate different weights to each facial part during processing. For deriving the weights, we analyzed data from a human face recognition experiment using eye-tracking. Eye-tracking allows us to determine the facial parts during the recognition process which represent salient regions for human processing. Face images are pre-processed during the recognition step using a weight mask based on the salient regions from the eye-tracking data. A comparison with the standard non-weighted LGBP approach demonstrates the efficacy of our method with the weighted method performing better under lighting changes.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Pages863-867
Number of pages5
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012 - Seoul, Korea, Republic of
Duration: 2012 Oct 142012 Oct 17

Other

Other2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012
CountryKorea, Republic of
CitySeoul
Period12/10/1412/10/17

Fingerprint

Face recognition
Lighting
Processing
Masks
Experiments

Keywords

  • eye-tracking
  • Face recognition
  • human perception
  • LGBP
  • lighting changes

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Human-Computer Interaction

Cite this

Choi, E., Lee, S. W., & Wallraven, C. (2012). Face recognition with enhanced local gabor binary pattern from human fixations. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (pp. 863-867). [6377836] https://doi.org/10.1109/ICSMC.2012.6377836

Face recognition with enhanced local gabor binary pattern from human fixations. / Choi, Eunsoo; Lee, Seong Whan; Wallraven, Christian.

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2012. p. 863-867 6377836.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, E, Lee, SW & Wallraven, C 2012, Face recognition with enhanced local gabor binary pattern from human fixations. in Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics., 6377836, pp. 863-867, 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012, Seoul, Korea, Republic of, 12/10/14. https://doi.org/10.1109/ICSMC.2012.6377836
Choi E, Lee SW, Wallraven C. Face recognition with enhanced local gabor binary pattern from human fixations. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2012. p. 863-867. 6377836 https://doi.org/10.1109/ICSMC.2012.6377836
Choi, Eunsoo ; Lee, Seong Whan ; Wallraven, Christian. / Face recognition with enhanced local gabor binary pattern from human fixations. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2012. pp. 863-867
@inproceedings{ed1547a8f2dd4143854f10978d7de8f0,
title = "Face recognition with enhanced local gabor binary pattern from human fixations",
abstract = "Performance of automatic face recognition algorithm has increased considerably over the past decades. However, face recognition under changes in lighting conditions remains a challenging issue for computers. In this paper, we propose a novel face recognition algorithm inspired by information taken from human fixation patterns. We augment a LGBP (Local Gabor Binary Pattern) algorithm - a well-known face recognition algorithm - to allocate different weights to each facial part during processing. For deriving the weights, we analyzed data from a human face recognition experiment using eye-tracking. Eye-tracking allows us to determine the facial parts during the recognition process which represent salient regions for human processing. Face images are pre-processed during the recognition step using a weight mask based on the salient regions from the eye-tracking data. A comparison with the standard non-weighted LGBP approach demonstrates the efficacy of our method with the weighted method performing better under lighting changes.",
keywords = "eye-tracking, Face recognition, human perception, LGBP, lighting changes",
author = "Eunsoo Choi and Lee, {Seong Whan} and Christian Wallraven",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICSMC.2012.6377836",
language = "English",
isbn = "9781467317146",
pages = "863--867",
booktitle = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - Face recognition with enhanced local gabor binary pattern from human fixations

AU - Choi, Eunsoo

AU - Lee, Seong Whan

AU - Wallraven, Christian

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Performance of automatic face recognition algorithm has increased considerably over the past decades. However, face recognition under changes in lighting conditions remains a challenging issue for computers. In this paper, we propose a novel face recognition algorithm inspired by information taken from human fixation patterns. We augment a LGBP (Local Gabor Binary Pattern) algorithm - a well-known face recognition algorithm - to allocate different weights to each facial part during processing. For deriving the weights, we analyzed data from a human face recognition experiment using eye-tracking. Eye-tracking allows us to determine the facial parts during the recognition process which represent salient regions for human processing. Face images are pre-processed during the recognition step using a weight mask based on the salient regions from the eye-tracking data. A comparison with the standard non-weighted LGBP approach demonstrates the efficacy of our method with the weighted method performing better under lighting changes.

AB - Performance of automatic face recognition algorithm has increased considerably over the past decades. However, face recognition under changes in lighting conditions remains a challenging issue for computers. In this paper, we propose a novel face recognition algorithm inspired by information taken from human fixation patterns. We augment a LGBP (Local Gabor Binary Pattern) algorithm - a well-known face recognition algorithm - to allocate different weights to each facial part during processing. For deriving the weights, we analyzed data from a human face recognition experiment using eye-tracking. Eye-tracking allows us to determine the facial parts during the recognition process which represent salient regions for human processing. Face images are pre-processed during the recognition step using a weight mask based on the salient regions from the eye-tracking data. A comparison with the standard non-weighted LGBP approach demonstrates the efficacy of our method with the weighted method performing better under lighting changes.

KW - eye-tracking

KW - Face recognition

KW - human perception

KW - LGBP

KW - lighting changes

UR - http://www.scopus.com/inward/record.url?scp=84872423625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872423625&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2012.6377836

DO - 10.1109/ICSMC.2012.6377836

M3 - Conference contribution

SN - 9781467317146

SP - 863

EP - 867

BT - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

ER -