Automation of Attendance System Using Facial Recognition

Abstract

The importance of a properly maintained attendance system is very high. Although many systems are already existing, there are many loopholes present. This paper presents an attendance system using face recognition, which is the best foot forward to reduce the loopholes encountered by these systems. The Attendance system using face recognition consists of two phases, face detection and face recognition. The performance of detection algorithms such as Viola Jones and deep learning-based detection was compared and deep learning-based detection was preferred. On the recognition front, deep learning-based face recognition was used and optimum results were obtained. It was found that dlib using Convolutional Neural Networks (CNN) yielded better results than dlib using Histogram Oriented Gradients (HOG) because HOG only detects a frontal image, while CNN detects faces from all angles and ensures no discrepancies during face detection and recognition. Also, it was observed that the speed of training datasets was higher in CNN as it uses GPU as compared to HOG, which uses CPU for training the dataset as well as recognition.