* Corresponding author: Ubong Essien Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0. A deep learning-based face recognition attendance system Ubong David Essien * and Godwin Okon Ansa Department of Computer Science, Faculty of Physical Sciences, Akwa Ibom State University Ikot Akpaden, Mkpat Enin. Global Journal of Engineering and Technology Advances, 2023, 17(01), 009–022 Publication history: Received on 10 July 2023; revised on 29 September 2023; accepted on 02 October 2023 Article DOI: https://doi.org/10.30574/gjeta.2023.17.1.0165 Abstract Deep learning-based face recognition system have produced high accuracy and better performance when compared to other methods of face recognition like the eigen faces. Modern face recognition systems consist of different phases such as face detection, face alignment, feature extraction, face representation and face recognition. This paper proposes a deep learning approach in developing a face recognition-based class attendance system. The Multitask Convolutional Neural Network (MTCNN) is used for the face detection and alignment phase and a lightweight hybrid high performance Deepface Python framework based on the ‘Deepface’ Deep Convolutional Neural Network is employed for the feature extraction, face representation and face recognition phases with FaceNet-512 pretrained model. Because Convolutional Neural Networks (CNNs) perform better with larger datasets, image augmentation will be used on the original photos to enlarge the tiny dataset. The attendance record is stored in a MySQL database and accessed by an Application Programming Interface (API) developed using Hypertext Pre-processor (PHP) CodeIgniter framework. Cosine Similarity is used as the similarity metrics to compare the facial embeddings. A sliding camera system is deployed to aids the full coverage of the class participants irrespective of the size of the class. The test result show that all class participants were correctly identified and captured in the class attendance register generated. Keywords: Deep Convolutional Neural Network; Application Programming Interface; Facial Embeddings; Image Augmentation 1. Introduction According to [10], empirical evidences have shown that there is a significant correlation between students who have poor attendances and their academic performances. Attendance is the single strongest predictor of college grades, according to a meta-analysis [4]. Face recognition systems have quickly surpassed other forms of biometrics such as Fingerprints, Radio Frequency Identification etc. as they use a set of features distinct to one person [7] According to [2], the issue of low-class attendance in higher learning institutions has been and continues to be a major concern for educators and educational researchers worldwide. The proposed system will be implemented in combination with a single sliding camera architecture [6]. The goal of this research is to improve the efficiency of the attendance system, eliminate impersonation, create secure access to attendance data, and save time that would otherwise be spent in the lecture. Existing facial recognition systems can be roughly classified into four types based on how the face is represented: - As previously mentioned, appearance-based, which employs holistic texture features. Model-based face recognition, which uses the shape and texture of the face as well as three-dimensional depth information; Template-based face recognition; and Neural network-based face recognition.