Josef Ström Bartunek

Fingerprint Recognition System: Implementation and Evaluation with Roc Graphs Using Mex-files Josef Ström Bartunek

Fingerprints are rich in details which are in the form of discontinuities in ridges known as minutiae which are unique for each person. The main desire of this book is to implement and evaluate National Institute of Science and Technology (NIST) Biometric Image Software (NBIS) for fingerprint recognition through extracting minutiae and matching the minutiae in MATLAB environment. Minutiae extraction and minutiae matching algorithms are in C-language and are interfaced with MATLAB using MEX-Files. A function is developed with NBIS for performing pre-processing and post-processing operations on the grayscale fingerprint images to extract good minutiae. The extracted minutiae are passed through the function with NBIS that match two minutiae patterns and produce a match score. Finally the performance of the system is evaluated on various fingerprint databases from different people and results are presented in Receiver Operating characteristics (ROC) graphs.