ABSTRACT
Fingerprint, being one of the most acceptable biometrics, has a huge modality of use for security purposes. In today's world, fingerprints are utilized in criminal investigations for identification purposes. Fingerprints can be used to identify a person's gender, hand, finger, and other relevant aspects. The required time and effort in identifying an individual can be reduced by gender, hand, and finger classifications using fingerprints. In this paper, a very simple model based on Convolutional Neural Networks (CNNs) is proposed to classify fingerprints by gender, hand, and finger. This research is conducted on the publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing). Our proposed model outperformed existing state-of-the-art approaches by a significant amount, with gender, hand, and finger accuracy rate of 96.50%, 97.83%, and 93.88%, respectively.
