Design & Implementation of Adaptive Fingerprint Biometrics with Training of DataSet

Abstract

This paper presents a fingerprint biometric system based on textures. In this work, it uses the training of image dataset for minimization of error. Fingerprint recognition is one of the oldest forms of biometric identification. However obtaining a good fingerprint image is not always easy. So the fingerprint image must be pre-processed before matching. The main objective of thesis is to design an image matching algorithm which is applied to any image for matching. The image will be of any size or any format. For this, the other objective is to present a better and enhanced fingerprint image. Commonly used features for improving fingerprint image quality are energy and local orientation. Accurate segmentation of fingerprint ridges from noisy background is necessary. For efficient enhancement and feature extraction algorithms, the segmented features must be void of any noise. A pre-processing method consisting of field orientation, ridge frequency estimation, filtering, segmentation and enhancement is performed. The obtained image is applied to a thinning algorithm and subsequent minutiae extraction. The methodology of image pre-processing and minutiae extraction is discussed. The simulations are performed in the MATLAB environment to evaluate the performance of the implemented algorithms. Results and observations of fingerprint images are presented at the end.