To Wrap, or Not to Wrap: Examining the Distinctions Between Model Implementations of Face Recognition on Mobile Devices in an Automatic Attendance System

• Published in: SN computer science 2023-11, Vol.4 (6), p.729, Article 729
• Main Authors: Tran, Trung-Dung, Ly, Tu-Nga
• Format: Article
• Language: English
• Subjects: Application programming interface; Cameras; Cellular telephones; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Data Structures and Information Theory; Deep learning; Educational objectives; Electronic devices; Face recognition; Future Data and Security Engineering 2022; Information Systems and Communication Service; Literature reviews; Machine learning; Original Research; Pattern Recognition and Graphics; Software Engineering/Programming and Operating Systems; Time and attendance systems; Vision
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-023-02185-2

As a continuation of the work that we had done in the past to develop an automatic attendance system for the campus of our institution, the following is stated—In this study, we will examine the differences in the implementation approaches of a face recognition model on actual mobile devices (iOS and Android), as well as its performance. Specifically, we will look at the discrepancies between these two categories. In particular, we will investigate the ways in which these distinctions influence the precision of face recognition predictions as well as the amount of work that is required of devices in order for them to use a machine learning model, examine the advantages and disadvantages of the model encoding approach that is shared by the TensorFlow and CoreML frameworks, as well as how it helps to the overall success of the AttendanceKit system.