Publication: The use of SOM for fingerprint classification
Date
2010
Authors
Turky A.M.
Ahmad M.S.
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The use of efficient classification methods is necessary for automatic fingerprint recognition systems. This paper introduces an approach to fingerprint classification by using Self-Organizing Maps (SOM). In order to be able to deal with fingerprint images having distorted regions, the SOM learning and classification algorithms are modified. The concept of 'certainty' is introduced and used in the modified algorithms. Our experiments show improved results with increasing network sizes. A network that is trained with a sufficiently large and representative set of samples can be used as an indexing mechanism for a fingerprint database, so that it does not need to be retrained for each fingerprint added to the database. �2010 IEEE.
Description
Keywords
Biometric , Fingerprint classification , Self organizing maps , Biometrics , Conformal mapping , Image recognition , Information retrieval , Knowledge management , Learning algorithms , Automatic fingerprint recognition system , Classification algorithm , Classification methods , Fingerprint classification , Fingerprint database , Fingerprint images , Indexing mechanisms , Modified algorithms , Network size , Self organizing maps