Robust Fingerprint Identification System Using Backpropagation and ART Neural Networks

	Nanotech 2008 Vol. 2 Nanotechnology 2008: Life Sciences, Medicine & Bio Materials - Technical Proceedings of the 2008 NSTI Nanotechnology Conference and Trade Show, Volume 2 Chapter 7: Bio & Chem Sensors
	Robust Fingerprint Identification System Using Backpropagation and ART Neural Networks
Authors:	A.A. Ilumoka, M. Talluri, M. Eng
Affilation:	University of Hartford, US
Pages:	622 - 628
Keywords:	biometric systems, fingerprint recognition, neural networks, artificial intelligence
Abstract:	This paper describes a robust minutiae-based fingerprint identification method suitable for use in small populations. System employs two serially connected neural networks in which fingerprint feature extraction is carried out by the first network – a backpropagation neural network and matching by the second - an adaptive resonance theory network which performs the decision making task of matching acquired fingerprint to templates in a database. The approach has been applied to a real database of noisy fingerprints derived from the 2002 Fingerprint Verification Competition (FVC2002) and has achieved error rates as low as 4% at penetration rates of 100%.
ISBN:	978-1-4200-8504-4
Pages:	808
Hardcopy:	$159.95

Order:	Mail/Fax Form
Up