Texture-Based Eyebrow Recognition

Mehmet Ozgur Turkoglu; Tugce Arican

doi:10.23919/BIOSIG.2017.8053522

Texture-Based Eyebrow Recognition

Mehmet Ozgur Turkoglu, Tugce Arican

Datamanagement & Biometrics

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

3 Citations (Scopus)

22 Downloads (Pure)

Abstract

Recent studies show that eyebrows can be used as a biometric or soft biometric for recognition. In some scenarios such as partially occluded or covered faces, they can be used for recognition. In this paper, we study eyebrow recognition using texture-based features. We apply features which have not been used before for eyebrow recognition such as 3-patch local binary pattern and WLD (Weber local descriptor) features. Also, we use more conventional features such as uniform LBP (Local binary pattern) and HOG (Histograms of oriented gradients). Methods are tested on both small- and large-sized datasets of images taken from FRGC database. Our experiments show that using some of these texture-based features together increases the performance significantly. We achieved more than 95% recognition accuracy for left and right eyebrows.

Original language	English
Title of host publication	2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017
Editors	Christoph Busch, Andreas Uhl, Arslan Bromme, Antitza Dantcheva, Christian Rathgeb
Place of Publication	Piscataway, NJ
Publisher	IEEE
ISBN (Electronic)	978-3-88579-664-0
ISBN (Print)	978-1-5386-0396-3
DOIs	https://doi.org/10.23919/BIOSIG.2017.8053522
Publication status	Published - 28 Sept 2017
Event	2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017 - Darmstadt, Germany Duration: 20 Sept 2017 → 22 Sept 2017

Conference

Conference	2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017
Abbreviated title	BIOSIG
Country/Territory	Germany
City	Darmstadt
Period	20/09/17 → 22/09/17

Keywords

3-patch LBP
4-patch LBP
Eyebrow recognition
HOG
LBP
Local descriptor
Texture-based
WLD
2024 OA procedure

Access to Document

10.23919/BIOSIG.2017.8053522

ArticleFinal published version, 16.9 MBLicence: Taverne

Cite this

@inproceedings{43321467593349d59a3280dcd82c3129,

title = "Texture-Based Eyebrow Recognition",

abstract = "Recent studies show that eyebrows can be used as a biometric or soft biometric for recognition. In some scenarios such as partially occluded or covered faces, they can be used for recognition. In this paper, we study eyebrow recognition using texture-based features. We apply features which have not been used before for eyebrow recognition such as 3-patch local binary pattern and WLD (Weber local descriptor) features. Also, we use more conventional features such as uniform LBP (Local binary pattern) and HOG (Histograms of oriented gradients). Methods are tested on both small- and large-sized datasets of images taken from FRGC database. Our experiments show that using some of these texture-based features together increases the performance significantly. We achieved more than 95% recognition accuracy for left and right eyebrows.",

keywords = "3-patch LBP, 4-patch LBP, Eyebrow recognition, HOG, LBP, Local descriptor, Texture-based, WLD, 2024 OA procedure",

author = "Turkoglu, {Mehmet Ozgur} and Tugce Arican",

year = "2017",

month = sep,

day = "28",

doi = "10.23919/BIOSIG.2017.8053522",

language = "English",

isbn = "978-1-5386-0396-3",

editor = "Christoph Busch and Andreas Uhl and Arslan Bromme and Antitza Dantcheva and Christian Rathgeb",

booktitle = "2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017",

publisher = "IEEE",

address = "United States",

note = "2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017, BIOSIG ; Conference date: 20-09-2017 Through 22-09-2017",

}

Turkoglu, MO & Arican, T 2017, Texture-Based Eyebrow Recognition. in C Busch, A Uhl, A Bromme, A Dantcheva & C Rathgeb (eds), 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017., 8053522, IEEE, Piscataway, NJ, 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017, Darmstadt, Hesse, Germany, 20/09/17. https://doi.org/10.23919/BIOSIG.2017.8053522

Texture-Based Eyebrow Recognition. / Turkoglu, Mehmet Ozgur; Arican, Tugce.
2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017. ed. / Christoph Busch; Andreas Uhl; Arslan Bromme; Antitza Dantcheva; Christian Rathgeb. Piscataway, NJ: IEEE, 2017. 8053522.

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

TY - GEN

T1 - Texture-Based Eyebrow Recognition

AU - Turkoglu, Mehmet Ozgur

AU - Arican, Tugce

PY - 2017/9/28

Y1 - 2017/9/28

N2 - Recent studies show that eyebrows can be used as a biometric or soft biometric for recognition. In some scenarios such as partially occluded or covered faces, they can be used for recognition. In this paper, we study eyebrow recognition using texture-based features. We apply features which have not been used before for eyebrow recognition such as 3-patch local binary pattern and WLD (Weber local descriptor) features. Also, we use more conventional features such as uniform LBP (Local binary pattern) and HOG (Histograms of oriented gradients). Methods are tested on both small- and large-sized datasets of images taken from FRGC database. Our experiments show that using some of these texture-based features together increases the performance significantly. We achieved more than 95% recognition accuracy for left and right eyebrows.

AB - Recent studies show that eyebrows can be used as a biometric or soft biometric for recognition. In some scenarios such as partially occluded or covered faces, they can be used for recognition. In this paper, we study eyebrow recognition using texture-based features. We apply features which have not been used before for eyebrow recognition such as 3-patch local binary pattern and WLD (Weber local descriptor) features. Also, we use more conventional features such as uniform LBP (Local binary pattern) and HOG (Histograms of oriented gradients). Methods are tested on both small- and large-sized datasets of images taken from FRGC database. Our experiments show that using some of these texture-based features together increases the performance significantly. We achieved more than 95% recognition accuracy for left and right eyebrows.

KW - 3-patch LBP

KW - 4-patch LBP

KW - Eyebrow recognition

KW - HOG

KW - LBP

KW - Local descriptor

KW - Texture-based

KW - WLD

KW - 2024 OA procedure

UR - http://www.scopus.com/inward/record.url?scp=85034600828&partnerID=8YFLogxK

U2 - 10.23919/BIOSIG.2017.8053522

DO - 10.23919/BIOSIG.2017.8053522

M3 - Conference contribution

AN - SCOPUS:85034600828

SN - 978-1-5386-0396-3

BT - 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017

A2 - Busch, Christoph

A2 - Uhl, Andreas

A2 - Bromme, Arslan

A2 - Dantcheva, Antitza

A2 - Rathgeb, Christian

PB - IEEE

CY - Piscataway, NJ

T2 - 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017

Y2 - 20 September 2017 through 22 September 2017

ER -

Texture-Based Eyebrow Recognition

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this