Deep Learning based Facial Recognition System for Attendance Maintenance

For attendance purposes, face recognition technology can be used to identify individuals within a company. In order to assess the effectiveness of any organisation, attendance records must be maintained and evaluated. Automating the conventional method of recording attendance is the aim of building an attendance monitoring system. The Yale face database has 95.76 percent of the Automated pictures. The Haar-cascade classifier and the LBPH (Local Binary Pattern Histogram) algorithm, both of which are implemented in Python and the OpenCV library, are used in our proposed model to identify the positive and negative features of the face. Numerous algorithms and techniques have been developed to enhance face recognition performance. The Tkinter GUI interface is utilised for user interface purposes. The everyday tasks of attendance marking and evaluation are handled by the attendance management system with less human interaction. For attendance purposes, face recognition technology can be used to identify individuals within a company. In order to assess the effectiveness of any organisation, attendance records must be maintained and evaluated. Automating the conventional method of recording attendance is the aim of building an attendance monitoring system. The everyday tasks of attendance marking and evaluation are handled with less human interaction thanks to the Automated Attendance Management System. The best outcomes from the algorithm, enhanced LBP, and PCA are then used to classify and recognise the facial images. The attendance of the identified student will then be noted and saved in an excel file. Students who sign in more than once will be alerted, and those who are not registered will be able to do so right away. When trained on two images per person, the average recognition accuracy for high-quality images is 100%, for low-quality images it is 94.11%, and for the Yale face database it is 95.76%. The Haar-cascade classifier and the LBPH (Local Binary Pattern Histogram) algorithm, both of which are implemented in Python and the OpenCV library, are used in our proposed model to identify the positive and negative features of the face. Numerous algorithms and techniques have been developed to enhance face recognition performance. The Tkinter GUI interface is utilised for user interface purposes.