Search: onr:"swepub:oai:DiVA.org:hh-21201" >
Automatic Measures ...
Automatic Measures for Predicting Performance in Off-line Signature
-
- Alonso-Fernandez, Fernando (author)
- Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain,ATVS/Biometric Recognition Group
-
- Fairhurst, M. (author)
- University of Kent, UK
-
- Fierrez, J. (author)
- Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain,ATVS/Biometric Recognition Group
-
show more...
-
- Ortega-Garcia, J. (author)
- Escuela Politecnica Superior, Univ. Autonoma de Madrid, Spain,ATVS/Biometric Recognition Group
-
show less...
-
Escuela Politecnica Superior, Univ Autonoma de Madrid, Spain ATVS/Biometric Recognition Group (creator_code:org_t)
- ISBN 9781424414376
- Piscataway, N.J. IEEE Press, 2007
- 2007
- English.
-
Series: IEEE International Conference on Image Processing ICIP, 1522-4880
- Related links:
-
https://hh.diva-port... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Performance in terms of accuracy is one of the most important goal of a biometric system. Hence, having a measure which is able to predict the performance with respect to a particular sample of interest is specially useful, and can be exploited in a number of ways. In this paper, we present two automatic measures for predicting the performance in off-line signature verification. Results obtained on a sub-corpus of the MCYT signature database confirms a relationship between the proposed measures and system error rates measured in terms of Equal Error Rate (EER), False Acceptance Rate (FAR) and False Rejection Rate (FRR). © 2007 IEEE.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
Keyword
- Biometrics
- Document image processing
- Handwriting recognition
- Pattern recognition
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database