Abstract

Presents a method of fingerprint classification. The method integrates a recognition system with a feedback mechanism, based on a genetic algorithm. The system was tested on 2000 images in the NIST-14 database. For the five-class problem, classification error was 6.0% without any rejects, and classification error approximated 1% with a 20% rejection rate. For the four-class problem (with two similar classes combined into the same class), classification error can be reduced to 5.2%. The results are better than those of the fingerprint classification systems created by Karu and Jian (1996) and by Blue et al. (1994). Through comparison experiments, it was illustrated that the feedback mechanism can give the recognition system the capability of adaptation to various inputs, and effectively improve its accuracy.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.