GAYE: A face recognition system

Burcu Kepenekci; F. Boray Tek; Onur Çilingir; Ufuk Sakarya; Gozde Bozdagi Akar

doi:10.1117/12.528919

GAYE: A face recognition system

Burcu Kepenekci^*, F. Boray Tek, Onur Çilingir, Ufuk Sakarya, Gozde Bozdagi Akar

^*Corresponding author for this work

Middle East Technical University

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

In this paper, a new face recognition system, GAYE, is presented. GAYE is a fully automatic system that detects and recognizes faces in cluttered scenes. The input of the system is any digitized image/image sequence that includes face/faces. The basic building blocks of the system are face detection, feature extraction and feature comparison. Face detection is based on skin color segmentation. For feature extraction, a novel approach is proposed that depends on the Gabor wavelet transform of the face image. By comparing facial feature vectors system finally makes a decision if the incoming person is recognized or not. Real time system tests show that GAYE achieves a recognition ratio over %90.

Original language	English
Pages (from-to)	99-106
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5298
DOIs	https://doi.org/10.1117/12.528919
Publication status	Published - 2004
Externally published	Yes
Event	Imaging Processing: Algorithms and Systems III - San Jose, CA, United States Duration: 19 Jan 2004 → 20 Jan 2004

Keywords

Face detection
Face recognition
Feature extraction
Gabor wavelet transform

Access to Document

10.1117/12.528919

Cite this

@article{ff0767f2cde9444f9fbaf23644600a97,

title = "GAYE: A face recognition system",

abstract = "In this paper, a new face recognition system, GAYE, is presented. GAYE is a fully automatic system that detects and recognizes faces in cluttered scenes. The input of the system is any digitized image/image sequence that includes face/faces. The basic building blocks of the system are face detection, feature extraction and feature comparison. Face detection is based on skin color segmentation. For feature extraction, a novel approach is proposed that depends on the Gabor wavelet transform of the face image. By comparing facial feature vectors system finally makes a decision if the incoming person is recognized or not. Real time system tests show that GAYE achieves a recognition ratio over %90.",

keywords = "Face detection, Face recognition, Feature extraction, Gabor wavelet transform",

author = "Burcu Kepenekci and {Boray Tek}, F. and Onur {\c C}ilingir and Ufuk Sakarya and Akar, {Gozde Bozdagi}",

year = "2004",

doi = "10.1117/12.528919",

language = "English",

volume = "5298",

pages = "99--106",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Imaging Processing: Algorithms and Systems III ; Conference date: 19-01-2004 Through 20-01-2004",

}

TY - JOUR

T1 - GAYE

T2 - Imaging Processing: Algorithms and Systems III

AU - Kepenekci, Burcu

AU - Boray Tek, F.

AU - Çilingir, Onur

AU - Sakarya, Ufuk

AU - Akar, Gozde Bozdagi

PY - 2004

Y1 - 2004

N2 - In this paper, a new face recognition system, GAYE, is presented. GAYE is a fully automatic system that detects and recognizes faces in cluttered scenes. The input of the system is any digitized image/image sequence that includes face/faces. The basic building blocks of the system are face detection, feature extraction and feature comparison. Face detection is based on skin color segmentation. For feature extraction, a novel approach is proposed that depends on the Gabor wavelet transform of the face image. By comparing facial feature vectors system finally makes a decision if the incoming person is recognized or not. Real time system tests show that GAYE achieves a recognition ratio over %90.

AB - In this paper, a new face recognition system, GAYE, is presented. GAYE is a fully automatic system that detects and recognizes faces in cluttered scenes. The input of the system is any digitized image/image sequence that includes face/faces. The basic building blocks of the system are face detection, feature extraction and feature comparison. Face detection is based on skin color segmentation. For feature extraction, a novel approach is proposed that depends on the Gabor wavelet transform of the face image. By comparing facial feature vectors system finally makes a decision if the incoming person is recognized or not. Real time system tests show that GAYE achieves a recognition ratio over %90.

KW - Face detection

KW - Face recognition

KW - Feature extraction

KW - Gabor wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=8844249298&partnerID=8YFLogxK

U2 - 10.1117/12.528919

DO - 10.1117/12.528919

M3 - Conference article

AN - SCOPUS:8844249298

SN - 0277-786X

VL - 5298

SP - 99

EP - 106

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

Y2 - 19 January 2004 through 20 January 2004

ER -

GAYE: A face recognition system

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this