Applications of Neural Networks in Fingerprint Identification

Abstract

The goal of this thesis is to investigate the current techniques for fingerprint identification system. This target can be mainly decomposed into image preprocessing, feature extraction and feature match. For each sub-task, some classical and up-to-date methods in literatures are analyzed. Based on the analysis, an integrated solution for fingerprint identification system is developed for demonstration. Fingerprint images are rarely of perfect quality. To achieve good minutiae extraction in fingerprints with varying quality, preprocessing in form of image enhancement and binarization is first applied on fingerprints before they are evaluated. We applied histogram equalization method for image enhancement to obtain a more reliable estimation of minutiae locations. To extract minutia points an algorithm based on crossing number method is used. Neural network trained for the location of these minutia points and to improve the performance of the system. An alignment-based elastic matching algorithm has been developed for minutia matching. This algorithm is capable of finding the correspondences between input minutia pattern and the stored template minutia pattern without resorting to exhaustive search. All the implementation work has been done in MATLAB 7.5.0 Image Processing Toolbox. Performance of the developed system is evaluated on a database with fingerprints from different people.