Biometric Recognition Based on Fingerprint: A Comparative Study
Bruno Matarazzo Duru, Jonas Mendonça Targino, Clodoaldo A. M. Lima · 2017
Fingerprint recognition is regarded as one of the most popular and reliable techniques for automatic personal identification due to the well-known distinctiveness and persistence of fingerprints. A critical issue in biometric system design is the choice of classifier. In this paper, we conducted a systematic performance evaluation of the five classifiers (Neural Networks, Support Vector Machines configured with radial basis function, Optimum Path Forest, K-nearest neighbors and Extreme Learning Machine) for the task of biometric recognition based on fingerprint. Experimental results conducted on a publicly available database are reported whereby we observe that the Support Vector Machine significantly outperform the others classifiers according to accuracy measure calculated.