Fingerprint classification system with feedback mechanism based on genetic algorithm
Qi Yuan, Jie Tian, Ruwei Dai · 2002
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.