A fully CNN based fingerprint recognition system

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.