Spectral Representations of Fingerprint Minutiae Subsets

Haiyun Xu; Raymond N.J. Veldhuis

doi:10.1109/CISP.2009.5302445

Spectral Representations of Fingerprint Minutiae Subsets

Haiyun Xu, Raymond N.J. Veldhuis

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

6 Citations (Scopus)

52 Downloads (Pure)

Abstract

The investigation of the privacy protection of biometric templates gains more and more attention. The spectral minutiae representation is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require as an input a fixed-length feature vector. However, the limited overlap of a fingerprint pair can reduce the performance of the spectral minutiae representation algorithm. Therefore, in this paper, we introduce the spectral representations of fingerprint minutiae subsets to cope with the limited overlap problem. In the experiment, we improve the recognition performance from 0.32% to 0.12% in equal error rate after applying the spectral representations of minutiae subsets algorithm.

Original language	English
Title of host publication	2nd International Congress on Image and Signal Processing, 2009 (CISP '09)
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Print)	978-1-4244-4131-0
DOIs	https://doi.org/10.1109/CISP.2009.5302445
Publication status	Published - Oct 2009
Event	2nd International Congress on Image and Signal Processing, CISP 2009 - Tianjin, China Duration: 17 Oct 2009 → 19 Oct 2009 Conference number: 2

Conference

Conference	2nd International Congress on Image and Signal Processing, CISP 2009
Abbreviated title	CISP
Country/Territory	China
City	Tianjin
Period	17/10/09 → 19/10/09

Keywords

SCS-Safety

Access to Document

10.1109/CISP.2009.5302445

Xu2009spectralFinal published version, 1.5 MB

Cite this

@inproceedings{3b5f94c15a164d2fa59ebeec2f2ddda3,

title = "Spectral Representations of Fingerprint Minutiae Subsets",

abstract = "The investigation of the privacy protection of biometric templates gains more and more attention. The spectral minutiae representation is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require as an input a fixed-length feature vector. However, the limited overlap of a fingerprint pair can reduce the performance of the spectral minutiae representation algorithm. Therefore, in this paper, we introduce the spectral representations of fingerprint minutiae subsets to cope with the limited overlap problem. In the experiment, we improve the recognition performance from 0.32% to 0.12% in equal error rate after applying the spectral representations of minutiae subsets algorithm.",

keywords = "SCS-Safety",

author = "Haiyun Xu and Veldhuis, {Raymond N.J.}",

year = "2009",

month = oct,

doi = "10.1109/CISP.2009.5302445",

language = "English",

isbn = "978-1-4244-4131-0",

pages = "1--5",

booktitle = "2nd International Congress on Image and Signal Processing, 2009 (CISP '09)",

publisher = "IEEE",

address = "United States",

note = "2nd International Congress on Image and Signal Processing, CISP 2009, CISP ; Conference date: 17-10-2009 Through 19-10-2009",

}

TY - GEN

T1 - Spectral Representations of Fingerprint Minutiae Subsets

AU - Xu, Haiyun

AU - Veldhuis, Raymond N.J.

N1 - Conference code: 2

PY - 2009/10

Y1 - 2009/10

N2 - The investigation of the privacy protection of biometric templates gains more and more attention. The spectral minutiae representation is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require as an input a fixed-length feature vector. However, the limited overlap of a fingerprint pair can reduce the performance of the spectral minutiae representation algorithm. Therefore, in this paper, we introduce the spectral representations of fingerprint minutiae subsets to cope with the limited overlap problem. In the experiment, we improve the recognition performance from 0.32% to 0.12% in equal error rate after applying the spectral representations of minutiae subsets algorithm.

AB - The investigation of the privacy protection of biometric templates gains more and more attention. The spectral minutiae representation is a novel method to represent a minutiae set as a fixed-length feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. These characteristics enable the combination of fingerprint recognition systems with template protection schemes that require as an input a fixed-length feature vector. However, the limited overlap of a fingerprint pair can reduce the performance of the spectral minutiae representation algorithm. Therefore, in this paper, we introduce the spectral representations of fingerprint minutiae subsets to cope with the limited overlap problem. In the experiment, we improve the recognition performance from 0.32% to 0.12% in equal error rate after applying the spectral representations of minutiae subsets algorithm.

KW - SCS-Safety

U2 - 10.1109/CISP.2009.5302445

DO - 10.1109/CISP.2009.5302445

M3 - Conference contribution

SN - 978-1-4244-4131-0

SP - 1

EP - 5

BT - 2nd International Congress on Image and Signal Processing, 2009 (CISP '09)

PB - IEEE

T2 - 2nd International Congress on Image and Signal Processing, CISP 2009

Y2 - 17 October 2009 through 19 October 2009

ER -