An Empirical Comparison of Individual Machine Learning Techniques in Signature and Fingerprint Classification

Abreu, M.C.D. and Fairhurst, M.C. (2008) An Empirical Comparison of Individual Machine Learning Techniques in Signature and Fingerprint Classification. In: Schouten, B. and Juul, N.C. and Drygajlo, A. and Tistarelli, M., eds. Biometrics and Identity Management: BOID 2008 (1st : 2008 : Roskilde, Denmark). Lecture Notes in Computer Science, 5372 . Springer, Berlin, pp. 130-139. ISBN 978-3-540-89990-7 ISSN 0302-9743 . (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)

Abstract

This paper describes an empirical study to investigate the performance of a wide range of classifiers deployed in applications to classify biometric data. The study specifically reports results based on two different modalities, the handwritten signature and fingerprint recognition. We demonstrate quantitatively how performance is related to classifier type, and also provide a finer-grained analysis to relate performance to specific non-biometric factors in population demographics. The paper discusses the implications for individual modalities, for multiclassifier but single modality systems, and for full multibiometric solutions.

Item Type: Book section
Additional information: First European Workshop on Biometrics and Identity Management (BIOID2008, Roskilde University, Denmark, 7-9 May 2008
Uncontrolled keywords: Classifiers, signature, fingerprints
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics (see also: telecommunications) > TK7880 Applications of electronics (inc industrial & domestic) > TK7882.B56 Biometrics
Divisions: Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts > Image and Information Engineering
Depositing User: J. Harries
Date Deposited: 10 Mar 2010 14:27
Last Modified: 10 Mar 2010 14:27
Resource URI: http://kar.kent.ac.uk/id/eprint/23128 (The current URI for this page, for reference purposes)
  • Depositors only (login required):