Fingerprint Recognition using Different Classifiers (ANN and k�NN)

Fatima Kamil Faek

Volume : VI, Issue : IX, September - 2016

Fingerprint Recognition using Different Classifiers (ANN and k�NN)

Fatima Kamil Faek

Abstract :

It is possible to identify any person from his/her fingerprint, since they cannot be shared or directed toward the wrong person. In this work a fingerprint recognizer is presented using two types of classifiers (k–NN and ANN). The used features are extracted using Haar mother wavelet. The aim of this work is to make a comparison between the k–NN and the ANN classifiers. In this work Levenberg–Marquardt error back propagation algorithm is used for the ANN classifier since it appears to be the fastest method for training moderate–sized feed forward neural networks . The result of using the k–NN classifier was 48%, while when using the ANN classifier the result is improved by 39%.The algorithm is evaluated using the fingerprints of 31 peoples (four versions per person) using mat lab program.