On Hunting Animals of the Biometric Menagerie for Online Signature.
Where this comes from
- Record sourced from PubMed, PMID 27054836.
- Also identified by DOI 10.1371/journal.pone.0151691 and PMC identifier 4824397.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Individuals behave differently regarding to biometric authentication systems. This fact was formalized in the literature by the concept of Biometric Menagerie, defining and labeling user groups with animal names in order to reflect their characteristics with respect to biometric systems. This concept was illustrated for face, fingerprint, iris, and speech modalities. The present study extends the Biometric Menagerie to online signatures, by proposing a novel methodology that ties specific quality measures for signatures to categories of the Biometric Menagerie. Such measures are combined for retrieving automatically writer categories of the extended version of the Biometric Menagerie. Performance analysis with different types of classifiers shows the pertinence of our approach on the well-known MCYT-100 database.
Medical subject headings
- Algorithms
- Biometric Identification
- Handwriting
- Online Systems
- Pattern Recognition, Automated