Evaluation of Supervised Machine Learning Classification Algorithms for Fingerprint Recognition

Abstract

This paper presents the application of the Classification Learner MATLAB tool from the Statistics and Machine Learning Toolbox for the classification process in a fingerprint recognition system based on the set B from the public databases FVC2000, FVC2002, and FVC2004. The general results indicate that this system can achieve high accuracy values for several sub-databases using multiple supervised machine learning algorithms including decision trees, discriminant analysis, support vector machines, logistic regression, nearest neighbors, naive Bayes, and ensemble classifiers. The highest accuracy value of 98.8% corresponding to the DB3-2000 subset was obtained using the ensemble subspace discriminant classifier.