Study of Deep Learning Methods for Fingerprint Recognition
Mamadou Diarra1, Ayikpa Kacoutchy Jean2, Ballo Abou Bakary3, Kouassi Brou Médard4
1Mamadou Diarra*, Assistant professor, Department of mathematics and computer sciences, University of Félix Houphouet
2Ayikpa Kacoutchy Jean, Teacher and Researcher,Department of Computer science and digital sciences, Virtual University
3Ballo Abou Bakary, Teacher and Researcher, Department of agropastoral management.
4Kouassi Brou Medard , IT Manager, University of Félix Houphouet
Manuscript received on September 17, 2021. | Revised Manuscript received on September 24, 2021. | Manuscript published on September 30, 2021. | PP: 192-197 | Volume-10 Issue-3, September 2021. | Retrieval Number: 100.1/ijrte.C64780910321 | DOI: 10.35940/ijrte.C6478.0910321
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Biometric systems aim to reliably identify and authenticate an individual using physiological or behavioral characteristics. Traditional systems such as the use of access cards, passwords have shown limitations such as forgotten passwords, stolen cards, etc. As an alternative, biometric systems present themselves as efficient systems with a high reliability due to the physiological characteristics of each individual. This paper focuses on a deep learning method for fingerprint recognition. The described architecture uses a pre-processing phase in which grayscale images are represented on the RGB bands and then merged to obtain color images. On the obtained color images will be extracted the characteristics of the fingerprints textures. The fingerprint images after preprocessing are used in a deep convolution network system for decision making. The method is robust with an accuracy of over 99.43% and 99.53% with the respective variants densenet-201 and ResNet-50.
Keywords: Deep learning; fingerprint authentification; Biometrics system; CNN; DenseNet-201; ResNet-50.