On ear biometrics

Bahattin Kocaman; Mürvet Kirci; Ece Olcay Güne; Yüksel Çakir; Oüzlem Oüzbudak

doi:10.1109/EURCON.2009.5167651

On ear biometrics

Bahattin Kocaman^*, Mürvet Kirci, Ece Olcay Güne, Yüksel Çakir, Oüzlem Oüzbudak

^*Corresponding author for this work

Department of Electronics and Communications Engineering

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

10 Citations (Scopus)

Abstract

Today the most successful biometric based identification technologies such as fingerprint, iris, retina, palm and face recognition are used worldwide in both criminal investigations and high security facilities. These technologies are well-studied, but research shows they have many drawbacks which decrease the success of the methods applied. Ear images are not affected by emotional expression, illumination, aging, poses and alike. In this study principal component analysis (PCA), fisher linear discriminant analysis (FLDA), discriminative common vector analysis (DCVA), and locality preserving projections (LPP) were applied to ear images for personal identification. The error and hit rates of four algorithms were calculated by random subsampling and k-fold cross validation.

Original language	English
Title of host publication	IEEE EUROCON 2009, EUROCON 2009
Pages	327-332
Number of pages	6
DOIs	https://doi.org/10.1109/EURCON.2009.5167651
Publication status	Published - 2009
Externally published	Yes
Event	IEEE EUROCON 2009, EUROCON 2009 - St. Petersburg, Russian Federation Duration: 18 May 2009 → 23 May 2009

Publication series

Name	IEEE EUROCON 2009, EUROCON 2009

Conference

Conference	IEEE EUROCON 2009, EUROCON 2009
Country/Territory	Russian Federation
City	St. Petersburg
Period	18/05/09 → 23/05/09

Keywords

DCVA
Ear biometrics
FLDA
LPP
PCA

Access to Document

10.1109/EURCON.2009.5167651

Cite this

@inproceedings{c99db1b9e0b742f59c3f16cd18a9cba7,

title = "On ear biometrics",

abstract = "Today the most successful biometric based identification technologies such as fingerprint, iris, retina, palm and face recognition are used worldwide in both criminal investigations and high security facilities. These technologies are well-studied, but research shows they have many drawbacks which decrease the success of the methods applied. Ear images are not affected by emotional expression, illumination, aging, poses and alike. In this study principal component analysis (PCA), fisher linear discriminant analysis (FLDA), discriminative common vector analysis (DCVA), and locality preserving projections (LPP) were applied to ear images for personal identification. The error and hit rates of four algorithms were calculated by random subsampling and k-fold cross validation.",

keywords = "DCVA, Ear biometrics, FLDA, LPP, PCA",

author = "Bahattin Kocaman and M{\"u}rvet Kirci and G{\"u}ne, {Ece Olcay} and Y{\"u}ksel {\c C}akir and O{\"u}zlem O{\"u}zbudak",

year = "2009",

doi = "10.1109/EURCON.2009.5167651",

language = "English",

isbn = "9781424438617",

series = "IEEE EUROCON 2009, EUROCON 2009",

pages = "327--332",

booktitle = "IEEE EUROCON 2009, EUROCON 2009",

note = "IEEE EUROCON 2009, EUROCON 2009 ; Conference date: 18-05-2009 Through 23-05-2009",

}

TY - GEN

T1 - On ear biometrics

AU - Kocaman, Bahattin

AU - Kirci, Mürvet

AU - Güne, Ece Olcay

AU - Çakir, Yüksel

AU - Oüzbudak, Oüzlem

PY - 2009

Y1 - 2009

N2 - Today the most successful biometric based identification technologies such as fingerprint, iris, retina, palm and face recognition are used worldwide in both criminal investigations and high security facilities. These technologies are well-studied, but research shows they have many drawbacks which decrease the success of the methods applied. Ear images are not affected by emotional expression, illumination, aging, poses and alike. In this study principal component analysis (PCA), fisher linear discriminant analysis (FLDA), discriminative common vector analysis (DCVA), and locality preserving projections (LPP) were applied to ear images for personal identification. The error and hit rates of four algorithms were calculated by random subsampling and k-fold cross validation.

AB - Today the most successful biometric based identification technologies such as fingerprint, iris, retina, palm and face recognition are used worldwide in both criminal investigations and high security facilities. These technologies are well-studied, but research shows they have many drawbacks which decrease the success of the methods applied. Ear images are not affected by emotional expression, illumination, aging, poses and alike. In this study principal component analysis (PCA), fisher linear discriminant analysis (FLDA), discriminative common vector analysis (DCVA), and locality preserving projections (LPP) were applied to ear images for personal identification. The error and hit rates of four algorithms were calculated by random subsampling and k-fold cross validation.

KW - DCVA

KW - Ear biometrics

KW - FLDA

KW - LPP

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=70449637683&partnerID=8YFLogxK

U2 - 10.1109/EURCON.2009.5167651

DO - 10.1109/EURCON.2009.5167651

M3 - Conference contribution

AN - SCOPUS:70449637683

SN - 9781424438617

T3 - IEEE EUROCON 2009, EUROCON 2009

SP - 327

EP - 332

BT - IEEE EUROCON 2009, EUROCON 2009

T2 - IEEE EUROCON 2009, EUROCON 2009

Y2 - 18 May 2009 through 23 May 2009

ER -

On ear biometrics

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this