ABSTRACT
The digitalization of human work has been an ever-evolving process. Student's and employee's attendance systems are automated by using fingerprint biometrics. Specifically covid situation has created the need for touchless attendance system. Many institutions have already implemented a face detection-based attendance system. However, the major problem in designing face-recognising biometric applications is the scalability and accuracy in time to differentiate between multiple faces from a single clip/image. This paper used the OpenFace model for face recognition and developed a multi-face recognition model. The Torch and Python deployment module of deep neural network-based face recognition was used, and it was predicated accurately in time. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
The digitalization of human work has been an ever-evolving process. Student’s and employee’s attendance systems are automated by using fingerprint biometrics. Specifically covid situation has created the need for touchless attendance system. Many institutions have already implemented a face detection-based attendance system. However, the major problem in designing face-recognising biometric applications is the scalability and accuracy in time to differentiate between multiple faces from a single clip/image. This paper used the OpenFace model for face recognition and developed a multi-face recognition model. The Torch and Python deployment module of deep neural network-based face recognition was used, and it was predicated accurately in time. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.