Image from paper
Image from paper
Marking of attendance is one of the oppressive tasks in a lecture. Moreover, it takes a lot of time to mark the attendance of students manually. Some of the problems need to be addressed regarding attendance marking are the possibility of a proxy, the analysis of attendance of a student which could include how frequently one is skipping the classes. In recent days, traditional methods of marking attendance are turning out burdensome tasks. A solution for automating the attendance system efficiently can be done by facial recognition and is also a thriving task in face recognition. However, the automation is done using biometric systems in past, but it is not an efficient way of doing as faking a fingerprint is much easier. And also the authenticity and accuracy signifies the methods to be chosen for this task, which many proposed methods lack. This research mainly focuses on the methods of marking attendance and firmly evaluate and analyze intelligent techniques to mark attendance. In this paper, we propose a novel method of marking attendance using facial recognition. The proposed method uses small and accurate deeply supervised network for recognition of faces in a wild classroom scenario. A web application is developed for easy inference to the users. All the analytics is performed on Amazon Elastic Compute Cloud (Amazon EC2) Instance.