Minutiae Extraction & Postprocessing in Fingerprint Recognition

Abstract

Existing security measures rely on knowledge-based approaches like passwords or token-based approaches such as magnetic cards and passports to control access to physical and virtual spaces. Such methods are not very secure. Tokens such as access control cards may be shared or stolen. Furthermore, they cannot differentiate between authorized user and a person having access to the tokens or passwords. Biometrics such as fingerprint, face and voice print offers means of reliable personal authentication that can address these problems and have good acceptance. Fingerprints were one of the first forms of biometric authentication to be used for law enforcement and civilian applications. A critical step in automatic fingerprint is to automatically and reliably extract minutiae from the input fingerprint images. However, the performance of a minutiae extraction algorithm relies heavily on the quality of the input fingerprint images. In order to ensure that the performance of an automatic fingerprint system will be robust with respect to the quality of input fingerprint images, it essential to incorporate a fingerprint enhancement algorithm in the minutiae extraction module. This thesis, firstly provide discussion on the methodology and techniques for fingerprint image enhancement and minutiae extraction. The thesis then implements minutiae extraction by using Cross Number (CN) technique and implements Postprocessing stage to remove spurious minutiae. The system is developed using Matlab V7 on Windows XP. The fingerprint database, used for testing the system, was provided by Biometric Systems Lab at University of Bologna, Italy: Fingerprint Verification Competition FVC2002. The success rate of the feature extraction and Postprocessing system is 86% and error rate is 14%.development of further constraints to reduce the amount of false error rate.