Fingerprint identification and recognition are considered popular technique\nin many security and law enforcement applications. The aim of this paper is to\npresent a proposed authentication system based on fingerprint as biometric\ntype, which is capable of recognizing persons with high level of confidence\nand minimum error rate. The designed system is implemented using Matlab\n2015b and tested on a set of fingerprint images gathered from 90 different\npersons with 8 samples for each using Futronic�s FS80 USB2.0 Fingerprint\nScanner and the ftrScanApiEx.exe program. An efficient image enhancement\nalgorithm is used to improve the clarity (contrast) of the ridge structures in a\nfingerprint. After that core point and candidate core points are extracted for\neach Fingerprint image and feature vector have been extracted for each point\nusing filterbank_based algorithm. Also, for the matching the KNN neural\nnetwork was used. In addition, the matching results were calculated and\ncompared to other papers using some performance evaluation factors. A\nthreshold has been proposed and used to provide the rejection for the fingerprint\nimages that does not belong to the database and the experimental results\nshow that the KNN technique have a recognition rate equal to 93.9683% in a\nthreshold equal to 70%.
Loading....