Enhancement the Attendance System in Educational Institutions Based on Image Processing and Facial Recognition

Abstract

Currently, accounting for student attendance is one of the key components for raising the calibre of specialized training. It is possible to automate this procedure. The article suggests using facial recognition technology, which enables you to identify multiple people at once without having to make direct contact with them or utilize pricey equipment, to create the attendance system in educational institutions. Based on the article's analysis of contemporary facial recognition techniques, this solution makes use of convolutional neural networks Retina Face and ResNet. Our attendance system's architecture is enhanced by image pre-processing techniques that, when needed, apply algorithms to the image to even out colours, sharpen edge, boost brightness, and reduce noise. These techniques are based on our suggested methodology, which is based on the BREN measure. The computer experiment results are shown, demonstrating the higher efficiency of the suggested approach in comparison to its equivalents.