MFLCNN Based Ai Attendance Wizard: The Next Generation App for Real-Time Attendance Evaluation Using Deep Learning

Abstract

A growing demand for efficient attendance evaluation systems is driving innovation. This research uses an interactive app to evaluate attendance in real-time attendance for college or office. Monitoring and managing attendance is made easier with automated face identification and analysis. In the interactive app, users can continuously capture, process, and evaluate attendance records. It is used here to compare the proposed attendance evaluation system to traditional methods. It is possible to solve the Traditional Method's problems with an authentic and smart attendance system. In attendance systems, biometrics such as face recognition and fingerprint recognition are becoming more prevalent. A face's unique features make it recognizable. Using an interactive app, this work evaluates and predicts the attendance of students in real-time. In the beginning, all departmental, academic, staff, and student information is uploaded to the server along with a student's unique ID. Using the staff's credentials, the Interactive App will capture real-time multi-face images for transmission to the server to generate an AI model (MFLCNN Classifier). A notification marks attendance by matching images with students in the database. It is demonstrated in this study that multi-face attendance evaluation in real time can improve accuracy, convenience, and reliability. It also reduces the time of the traditional attendance process.