Quality Estimation for Vascular Pattern Recognition

Daniel Hartung; Sophie Martin; Christoph Busch

doi:10.1109/ICHB.2011.6094332

Quality Estimation for Vascular Pattern Recognition

Daniel Hartung, Sophie Martin, Christoph Busch

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

Abstract

The quality of captured samples is a critical aspect in biometric systems. In this paper we present a quality estimation algorithm for vascular images, which uses global and local features based on a Grey Level Co-Occurrence Matrix (GLCM) and optionally available metadata. An evaluation of the algorithm using different processing methods and vein sample databases shows convincing results: disregarding low estimated quality sample images helps to increase the performance. Moreover, metadata gives accurate indications on sample quality. The algorithm works on low level raw images, it is fast and therefore qualified to be used in feedback mode during enrolment or verification operation.

Original language	English
Title of host publication	2011 International Conference on Hand-Based Biometrics (ICHB)
Publisher	IEEE
Publication date	2011
ISBN (Print)	978-1-4577-0491-8
ISBN (Electronic)	978-1-4577-0489-5
DOIs	https://doi.org/10.1109/ICHB.2011.6094332
Publication status	Published - 2011
Event	International Conference on Hand-Based Biometrics 2011 - Hong Kong, China Duration: 17 Nov 2011 → 18 Nov 2011

Conference

Conference	International Conference on Hand-Based Biometrics 2011
Country/Territory	China
City	Hong Kong
Period	17/11/2011 → 18/11/2011

Access to Document

10.1109/ICHB.2011.6094332

http://ichb2011.comp.polyu.edu.hk/

OpenUrl availability

Full text

Cite this

@inproceedings{a14bd20fbe3d47d3beaf88f20531735f,

title = "Quality Estimation for Vascular Pattern Recognition",

abstract = "The quality of captured samples is a critical aspect in biometric systems. In this paper we present a quality estimation algorithm for vascular images, which uses global and local features based on a Grey Level Co-Occurrence Matrix (GLCM) and optionally available metadata. An evaluation of the algorithm using different processing methods and vein sample databases shows convincing results: disregarding low estimated quality sample images helps to increase the performance. Moreover, metadata gives accurate indications on sample quality. The algorithm works on low level raw images, it is fast and therefore qualified to be used in feedback mode during enrolment or verification operation.",

author = "Daniel Hartung and Sophie Martin and Christoph Busch",

year = "2011",

doi = "10.1109/ICHB.2011.6094332",

language = "English",

isbn = "978-1-4577-0491-8",

booktitle = "2011 International Conference on Hand-Based Biometrics (ICHB)",

publisher = "IEEE",

address = "United States",

note = "International Conference on Hand-Based Biometrics 2011, ICHB 2011 ; Conference date: 17-11-2011 Through 18-11-2011",

}

TY - GEN

T1 - Quality Estimation for Vascular Pattern Recognition

AU - Hartung, Daniel

AU - Martin, Sophie

AU - Busch, Christoph

PY - 2011

Y1 - 2011

N2 - The quality of captured samples is a critical aspect in biometric systems. In this paper we present a quality estimation algorithm for vascular images, which uses global and local features based on a Grey Level Co-Occurrence Matrix (GLCM) and optionally available metadata. An evaluation of the algorithm using different processing methods and vein sample databases shows convincing results: disregarding low estimated quality sample images helps to increase the performance. Moreover, metadata gives accurate indications on sample quality. The algorithm works on low level raw images, it is fast and therefore qualified to be used in feedback mode during enrolment or verification operation.

AB - The quality of captured samples is a critical aspect in biometric systems. In this paper we present a quality estimation algorithm for vascular images, which uses global and local features based on a Grey Level Co-Occurrence Matrix (GLCM) and optionally available metadata. An evaluation of the algorithm using different processing methods and vein sample databases shows convincing results: disregarding low estimated quality sample images helps to increase the performance. Moreover, metadata gives accurate indications on sample quality. The algorithm works on low level raw images, it is fast and therefore qualified to be used in feedback mode during enrolment or verification operation.

U2 - 10.1109/ICHB.2011.6094332

DO - 10.1109/ICHB.2011.6094332

M3 - Article in proceedings

SN - 978-1-4577-0491-8

BT - 2011 International Conference on Hand-Based Biometrics (ICHB)

PB - IEEE

T2 - International Conference on Hand-Based Biometrics 2011

Y2 - 17 November 2011 through 18 November 2011

ER -

Quality Estimation for Vascular Pattern Recognition

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this