Techniques of Binarization, Thinning and Feature Extraction Applied to a Fingerprint System

Abstract

A large volume of images of fingerprints are collected and stored to be used in various systems such as in access control and iden- tification records (ID). Systems for automatic fingerprint recogni- tion perform searches and comparisons with a database. Biometric recognition is based on two fundamental premises: the first is that digital printing must have permanent details, and the second is the information unit. From these premises, a system analyzes the fin- gerprint image to extract the information and then compares the data in the verification mode or identification mode. , Extraction techniques must be used to obtain the fingerprint data. These tech- niques use binarization, thinning and features extraction algorithms which are computational methods that can be applied to digital im- age processing used in scientific research and security issues. This paper presents a comparative analysis of four thresholding tech- niques (Niblack, Bernsen, Fisher, Fuzzy), two thinning techniques (Stentiford and Holt) and a feature extraction (Cross Number) tech- nique to evaluate the best performance of the algorithms in finger- print images. To develop this project a set of 160 fingerprint images was used in experiments and analysis. The results point out the pos- itive and negative points of the different algorithms. The system was developed in the C/C++ language.