WestminsterResearch

A fully CNN based fingerprint recognition system

Abrishambaf, Reza and Demirel, Hasan and Kale, Izzet (2008) A fully CNN based fingerprint recognition system. In: IEEE 11th Cellular Neural Networks and Their Applications (CNNA 2008). IEEE, pp. 146-149. ISBN 9781424420896

[img]
Preview
PDF
1967Kb

Official URL: http://dx.doi.org/10.1109/CNNA.2008.4588667

Abstract

In this paper, a fully cellular neural networks (CNN) based fingerprint recognition system is introduced. The system includes a preprocessing phase where the input fingerprint image is enhanced and a recognition phase where the enhanced fingerprint image is matched with the fingerprints in the database. Both preprocessing and recognition phases are realized by means of CNN approaches. A novel application of skeletonization method is used to perform ridgeline thinning which improves the quality of the extracted lines for further processing, and hence increases the overall system performance.

Item Type:Book Section
Research Community:University of Westminster > Electronics and Computer Science, School of
ID Code:7399
Deposited On:28 Jan 2010 18:28
Last Modified:12 Aug 2010 10:09

Repository Staff Only: item control page