Finger print Feature Extraction And Recognition System

Abstract

In the field of biometric authentication, i.e. verification or identification of an individual by personal features, a lot of research and development has been performed during the last few decades. Many biometric products have been developed and are now used in various application areas. Fingerprints have been used for over a century and are the most widely used form of biometric identification. Fingerprint identification is commonly employed in forensic science to support criminal investigations.

The fingerprint of an individual is unique and remains unchanged over a lifetime. A fingerprint is formed from an impression of the pattern of ridges on a finger. The minutiae, which are the local discontinuities in the ridge flow pattern, provide the features that are used for identification.

The main objective of the project is to extract the features from the fingerprint and match with the existing neural network database. This project is of research type and it took time in literature survey, design algorithms and training the features on Neural Network. The algorithms are developed using Microsoft C#.NET and pre-developed class libraries are used for matching data in Neural Network.