A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features

Raymond N.J. Veldhuis; A.M. Bazen; Wim Booij; A.J. Hendrikse; Anne Hendrikse

A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features

Raymond N.J. Veldhuis, A.M. Bazen, Wim Booij, A.J. Hendrikse, Anne Hendrikse

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

68 Downloads (Pure)

Abstract

This paper compares the performance of hand-geometry recognition based on high-level features and on low-level features. The difference between high- and low-level features is that the former are based on interpreting the biometric data, e.g. by locating a finger and measuring its dimensions, whereas the latter are not. The low-level features used here are landmarks on the contour of the hand. The high-level features are a standard set of geometrical features such as widths and lengths of fingers and angles, measured at preselected locations.

Original language	Undefined
Title of host publication	15th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)
Place of Publication	Utrecht, The Netherlands
Publisher	STW
Pages	326-330
Number of pages	5
ISBN (Print)	90-73461-43-X
Publication status	Published - Nov 2004
Event	15th Annual Workshop on Circuits, Systems and Signal Processing, ProRisc 2004 - Veldhoven, Netherlands Duration: 25 Nov 2004 → 26 Nov 2004 Conference number: 15

Publication series

Name
Publisher	STW/NWO/Dutch Ministry of Economic Affairs

Conference

Conference	15th Annual Workshop on Circuits, Systems and Signal Processing, ProRisc 2004
Abbreviated title	ProRisc
Country/Territory	Netherlands
City	Veldhoven
Period	25/11/04 → 26/11/04

Keywords

Landmarks
Hand geometry
EWI-788
SCS-Safety
hand contour
Biometric verification
IR-48121
METIS-219316

Access to Document

Cite this

@inproceedings{5d627591a304450cb3ef39794fb3444b,

title = "A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features",

abstract = "This paper compares the performance of hand-geometry recognition based on high-level features and on low-level features. The difference between high- and low-level features is that the former are based on interpreting the biometric data, e.g. by locating a finger and measuring its dimensions, whereas the latter are not. The low-level features used here are landmarks on the contour of the hand. The high-level features are a standard set of geometrical features such as widths and lengths of fingers and angles, measured at preselected locations.",

keywords = "Landmarks, Hand geometry, EWI-788, SCS-Safety, hand contour, Biometric verification, IR-48121, METIS-219316",

author = "Veldhuis, {Raymond N.J.} and A.M. Bazen and Wim Booij and A.J. Hendrikse and Anne Hendrikse",

note = "Imported from DIES; null ; Conference date: 25-11-2004 Through 26-11-2004",

year = "2004",

month = nov,

language = "Undefined",

isbn = "90-73461-43-X",

publisher = "STW",

pages = "326--330",

booktitle = "15th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)",

}

Veldhuis, RNJ, Bazen, AM, Booij, W, Hendrikse, AJ & Hendrikse, A 2004, A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features. in 15th Annual Workshop on Circuits Systems and Signal Processing (ProRISC). STW, Utrecht, The Netherlands, pp. 326-330, 15th Annual Workshop on Circuits, Systems and Signal Processing, ProRisc 2004, Veldhoven, Netherlands, 25/11/04.

A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features. / Veldhuis, Raymond N.J.; Bazen, A.M.; Booij, Wim et al.

15th Annual Workshop on Circuits Systems and Signal Processing (ProRISC). Utrecht, The Netherlands : STW, 2004. p. 326-330.

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

TY - GEN

T1 - A Comparison of Hand-Geometry Recognition Methods Based on Low- and High-Level Features

AU - Veldhuis, Raymond N.J.

AU - Bazen, A.M.

AU - Booij, Wim

AU - Hendrikse, A.J.

AU - Hendrikse, Anne

N1 - Conference code: 15

PY - 2004/11

Y1 - 2004/11

N2 - This paper compares the performance of hand-geometry recognition based on high-level features and on low-level features. The difference between high- and low-level features is that the former are based on interpreting the biometric data, e.g. by locating a finger and measuring its dimensions, whereas the latter are not. The low-level features used here are landmarks on the contour of the hand. The high-level features are a standard set of geometrical features such as widths and lengths of fingers and angles, measured at preselected locations.

AB - This paper compares the performance of hand-geometry recognition based on high-level features and on low-level features. The difference between high- and low-level features is that the former are based on interpreting the biometric data, e.g. by locating a finger and measuring its dimensions, whereas the latter are not. The low-level features used here are landmarks on the contour of the hand. The high-level features are a standard set of geometrical features such as widths and lengths of fingers and angles, measured at preselected locations.

KW - Landmarks

KW - Hand geometry

KW - EWI-788

KW - SCS-Safety

KW - hand contour

KW - Biometric verification

KW - IR-48121

KW - METIS-219316

M3 - Conference contribution

SN - 90-73461-43-X

SP - 326

EP - 330

BT - 15th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)

PB - STW

CY - Utrecht, The Netherlands

Y2 - 25 November 2004 through 26 November 2004

ER -