Fingerprint recognition for distorted image applications using three-rate hybrid Kohonen neural network

Authors:
Igor Astrov;Svetlana Tatarly;Sergei Tatarly;Ennu Rüstern
Affiliations:
Department of Computer Control, Tallinn University of Technology, Tallinn, Estonia;Department of Computer Control, Tallinn University of Technology, Tallinn, Estonia;Department of Computer Control, Tallinn University of Technology, Tallinn, Estonia;Department of Computer Control, Tallinn University of Technology, Tallinn, Estonia
Venue:
WAMUS'07 Proceedings of the 7th WSEAS international conference on Wavelet analysis & multirate systems
Year:
2007

Citing 4
Cited 1

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Performance Evaluation of Fingerprint Verification Systems

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Warping Using Ridge Curve Correspondences

IEEE Transactions on Pattern Analysis and Machine Intelligence
A new algorithm for distorted fingerprints matching based on normalized fuzzy similarity measure

IEEE Transactions on Image Processing

Characterization of Ag-PEO10LiCF3SO3-polypyrrol-Au neural switch

WSEAS Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of the most difficult problems in fingerprint recognition has been that the recognition performance is significantly influenced by distorted fingertip surface condition, which may vary depending on environmental or personal causes. Addressing this problem, this paper presents the three-rate hybrid Kohonen neural network (TRHKNN) for distorted fingerprint image processing. The received TRHKNN consists of "fast" Kohonen neural network (FKNN), "middle" Kohonen neural network (MKNN) and "slow" Kohonen neural network (SKNN). The received TRHKNN has not only high speed of image recognition, but also high speed of image restoration. This approach demonstrates that the proposed TRHKNN is capable not only to identify the distorted image of fingerprint but also to restore the undistorted image of fingerprint. The simulations for TRHKNN were carried out in a MATLAB/Simulink environment. This example shows the computing procedure and applicability of TRHKNN for fast-acting image recognition in real-time conditions.