Palmprint authentication using multiple classifiers

Ajay Kumar Pathak; Dapeng Zhang

doi:10.1117/12.542764

Palmprint authentication using multiple classifiers

Ajay Kumar Pathak, Dapeng Zhang

Research output: Journal article publication › Conference article › Academic research › peer-review

16 Citations (Scopus)

Abstract

This paper investigates the performance improvement for palmprint authentication using multiple classifiers. The proposed methods on personal authentication using palmprints can be divided into three categories; appearance-, line -, and texture-based. A combination of these approaches can be used to achieve higher performance. We propose to simultaneously extract palmprint features from PCA, Line detectors and Gabor-filters and combine their corresponding matching scores. This paper also investigates the comparative performance of simple combination rules and the hybrid fusion strategy to achieve performance improvement. Our experimental results on the database of 100 users demonstrate the usefulness of such approach over those based on individual classifiers.

Original language	English
Pages (from-to)	20-29
Number of pages	10
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5404
DOIs	https://doi.org/10.1117/12.542764
Publication status	Published - 1 Dec 2004
Event	Biometric Technology for Human Identification - Orlando, FL, United States Duration: 12 Apr 2004 → 13 Apr 2004

Keywords

Biometrics
Combination Rules
Fusion
Multiple Classifiers
Palmprint Authentication

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

More information

10.1117/12.542764

Cite this

@article{fdf4436830994fbbb225118a88c87637,

title = "Palmprint authentication using multiple classifiers",

abstract = "This paper investigates the performance improvement for palmprint authentication using multiple classifiers. The proposed methods on personal authentication using palmprints can be divided into three categories; appearance-, line -, and texture-based. A combination of these approaches can be used to achieve higher performance. We propose to simultaneously extract palmprint features from PCA, Line detectors and Gabor-filters and combine their corresponding matching scores. This paper also investigates the comparative performance of simple combination rules and the hybrid fusion strategy to achieve performance improvement. Our experimental results on the database of 100 users demonstrate the usefulness of such approach over those based on individual classifiers.",

keywords = "Biometrics, Combination Rules, Fusion, Multiple Classifiers, Palmprint Authentication",

author = "Pathak, {Ajay Kumar} and Dapeng Zhang",

year = "2004",

month = dec,

day = "1",

doi = "10.1117/12.542764",

language = "English",

volume = "5404",

pages = "20--29",

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

issn = "0277-786X",

publisher = "SPIE",

note = "Biometric Technology for Human Identification ; Conference date: 12-04-2004 Through 13-04-2004",

}

TY - JOUR

T1 - Palmprint authentication using multiple classifiers

AU - Pathak, Ajay Kumar

AU - Zhang, Dapeng

PY - 2004/12/1

Y1 - 2004/12/1

N2 - This paper investigates the performance improvement for palmprint authentication using multiple classifiers. The proposed methods on personal authentication using palmprints can be divided into three categories; appearance-, line -, and texture-based. A combination of these approaches can be used to achieve higher performance. We propose to simultaneously extract palmprint features from PCA, Line detectors and Gabor-filters and combine their corresponding matching scores. This paper also investigates the comparative performance of simple combination rules and the hybrid fusion strategy to achieve performance improvement. Our experimental results on the database of 100 users demonstrate the usefulness of such approach over those based on individual classifiers.

AB - This paper investigates the performance improvement for palmprint authentication using multiple classifiers. The proposed methods on personal authentication using palmprints can be divided into three categories; appearance-, line -, and texture-based. A combination of these approaches can be used to achieve higher performance. We propose to simultaneously extract palmprint features from PCA, Line detectors and Gabor-filters and combine their corresponding matching scores. This paper also investigates the comparative performance of simple combination rules and the hybrid fusion strategy to achieve performance improvement. Our experimental results on the database of 100 users demonstrate the usefulness of such approach over those based on individual classifiers.

KW - Biometrics

KW - Combination Rules

KW - Fusion

KW - Multiple Classifiers

KW - Palmprint Authentication

UR - http://www.scopus.com/inward/record.url?scp=8844250196&partnerID=8YFLogxK

U2 - 10.1117/12.542764

DO - 10.1117/12.542764

M3 - Conference article

SN - 0277-786X

VL - 5404

SP - 20

EP - 29

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

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

T2 - Biometric Technology for Human Identification

Y2 - 12 April 2004 through 13 April 2004

ER -

Palmprint authentication using multiple classifiers

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this