A proposed model for fingerprint recognition based on convolutional neural networks

Abstract

In recent years, deep learning has been applied to different computer vision problems across various sectors. The convolutional neural network (CNN) is one of the most important and widely used models, especially in image classification. In this paper, we propose a new model based on CNN to obtain high accuracy in fingerprint image classification. This model was trained and tested using two sub-datasets from the Sokoto Coventry Fingerprint Dataset (SOCOfing). The first was a real dataset consisting of 6000 original fingerprint images and the second consisted of hard-altered versions of 6000 images. The proposed model achieved a classification accuracy of 99.98%, precision of 100%, recall of 100% and F1 Score of 100% with the real dataset and an accuracy of 98.94%, precision of 99.00% and recall of 99.00% with the hard-altered dataset.