A fully CNN based fingerprint recognition system

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 datab...

Full description

Saved in:
Bibliographic Details
Published in2008 11th International Workshop on Cellular Neural Networks and Their Applications pp. 146 - 149
Main Authors Abrishambaf, R., Demirel, H., Kale, I.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2008
Subjects
Cellular neural networks
Feature extraction
Filtering
Fingerprint recognition
Image matching
Image processing
System performance
Online AccessGet full text
ISBN142442089X
9781424420896
ISSN2165-0144
DOI10.1109/CNNA.2008.4588667

Cover

More Information
Summary: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.
ISBN:142442089X
9781424420896
ISSN:2165-0144
DOI:10.1109/CNNA.2008.4588667