Face Recognition Smart Attendance System using Deep Transfer Learning
Khawla Alhanaee, Mitha Alhammadi, Nahla Almenhali, Maad Shatnawi
Abstract
Face identification has been considered an interesting research domain in the past few years as it plays a major biometric authentication role in several applications including attendance management and access control systems. Attendance management systems are very important to all organization though they are complex and time-consuming for managing regular attendance log. There are many automated human identification techniques such as biometrics, RFID, eye tracking, voice recognition. Face is one of the most broadly used biometrics for human identity authentication. This paper presents a facial recognition attendance system based on deep learning convolutional neural networks. We utilize transfer learning by using three pre-trained convolutional neural networks and trained them on our data. The three networks showed very high performance in terms of high prediction accuracy and reasonable training time.