Finger-Knuckle-Print recognition using BLPOC-based local block matching

Shoichiro Aoyama; Koichi Ito; Takafumi Aoki

doi:10.1109/ACPR.2011.6166641

Finger-Knuckle-Print recognition using BLPOC-based local block matching

Shoichiro Aoyama, Koichi Ito, Takafumi Aoki

情報学研究科・情報基礎科学専攻

研究成果: Conference contribution

20 被引用数 (Scopus)

抄録

This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching is successfully applied to image recognition tasks for biometric authentication applications. To calculate the matching score, the proposed algorithm corrects the global and local distortion between FKP images using the BLPOC-based local block matching. Experimental evaluation using the PolyU FKP database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional algorithms.

本文言語	English
ホスト出版物のタイトル	1st Asian Conference on Pattern Recognition, ACPR 2011
ページ	525-529
ページ数	5
DOI	https://doi.org/10.1109/ACPR.2011.6166641
出版ステータス	Published - 2011 12 1
イベント	1st Asian Conference on Pattern Recognition, ACPR 2011 - Beijing, China 継続期間: 2011 11 28 → 2011 11 28

出版物シリーズ

名前	1st Asian Conference on Pattern Recognition, ACPR 2011

Other

Other	1st Asian Conference on Pattern Recognition, ACPR 2011
Country	China
City	Beijing
Period	11/11/28 → 11/11/28

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

文献へのアクセス

10.1109/ACPR.2011.6166641

フィンガープリント「Finger-Knuckle-Print recognition using BLPOC-based local block matching」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル

@inproceedings{bead3ee559c3428bb65bd9aa02f41e46,

title = "Finger-Knuckle-Print recognition using BLPOC-based local block matching",

abstract = "This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching is successfully applied to image recognition tasks for biometric authentication applications. To calculate the matching score, the proposed algorithm corrects the global and local distortion between FKP images using the BLPOC-based local block matching. Experimental evaluation using the PolyU FKP database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional algorithms.",

keywords = "biometrics, finger-knuckle-print, local block matching, phase-only correlation",

author = "Shoichiro Aoyama and Koichi Ito and Takafumi Aoki",

year = "2011",

month = dec,

day = "1",

doi = "10.1109/ACPR.2011.6166641",

language = "English",

isbn = "9781457701221",

series = "1st Asian Conference on Pattern Recognition, ACPR 2011",

pages = "525--529",

booktitle = "1st Asian Conference on Pattern Recognition, ACPR 2011",

note = "1st Asian Conference on Pattern Recognition, ACPR 2011 ; Conference date: 28-11-2011 Through 28-11-2011",

}

TY - GEN

T1 - Finger-Knuckle-Print recognition using BLPOC-based local block matching

AU - Aoyama, Shoichiro

AU - Ito, Koichi

AU - Aoki, Takafumi

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching is successfully applied to image recognition tasks for biometric authentication applications. To calculate the matching score, the proposed algorithm corrects the global and local distortion between FKP images using the BLPOC-based local block matching. Experimental evaluation using the PolyU FKP database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional algorithms.

AB - This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching is successfully applied to image recognition tasks for biometric authentication applications. To calculate the matching score, the proposed algorithm corrects the global and local distortion between FKP images using the BLPOC-based local block matching. Experimental evaluation using the PolyU FKP database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional algorithms.

KW - biometrics

KW - finger-knuckle-print

KW - local block matching

KW - phase-only correlation

UR - http://www.scopus.com/inward/record.url?scp=84862894002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862894002&partnerID=8YFLogxK

U2 - 10.1109/ACPR.2011.6166641

DO - 10.1109/ACPR.2011.6166641

M3 - Conference contribution

AN - SCOPUS:84862894002

SN - 9781457701221

T3 - 1st Asian Conference on Pattern Recognition, ACPR 2011

SP - 525

EP - 529

BT - 1st Asian Conference on Pattern Recognition, ACPR 2011

T2 - 1st Asian Conference on Pattern Recognition, ACPR 2011

Y2 - 28 November 2011 through 28 November 2011

ER -