Facial Recognition-Based Student Attendance System

Face recognition holds significance in image processing and serves as a vital application in the technical domain. Its role is pivotal, particularly in authentication tasks, such as recording student attendance. A system for tracking attendance utilizing facial recognition involves the identification of students through the analysis of their facial characteristics, employing advanced monitoring technology and computer algorithms. The creation of this system aims to modernize the conventional method of recording attendance, which typically entails verbally calling out names and manually keeping track of attendance using pen and paper. The existing manual method for recording attendance is laborious and consumes a significant amount of time, and there's a risk of attendance data being altered easily. Traditional methods of recording attendance, along with current biometric systems, are susceptible to being bypassed by proxies. This paper presents a solution to tackle these challenges. The proposed system incorporates SVM, Haar classifiers, CNN, KNN, Gabor filters, and Generative Adversarial Networks for facial recognition. Post-facial identification and attendance records are produced and saved in Excel format. The system undergoes testing across different scenarios, including varying light conditions, head motions, and changes in the distance between the student and the camera. Following thorough testing, the system's overall complexity and accuracy were assessed. The proposed solution has demonstrated effectiveness and resilience as a tool for classroom attendance management, eliminating the need for manual labor and time consumption. The system is economically efficient and needs only minimal installation.