The Future of Multimedia: Micro Facial Recognition in Advanced Systems

Paper attendance systems are still widely used at many universities, consuming significant amounts of valuable classroom time. Furthermore, the system is likely to fail due to the possibility of human mistake and the rising chance of records being misplaced or lost altogether. The authors overcame this issue by automatically posting attendance information using a facial recognition software. This strategy also helps the school take a look at the student's financial situation. Attendance records and a list of slackers might be generated by the system. They can notify students and guardians via email of attendance and financial obligations. Using KNN deep learning methodology, photos taken by a CC camera or cell phone mounted at the door are used to identify students as they enter the classroom. This study incorporates ResNet and KNN-based Deep-learning technologies to extract useful information from low-quality photos. They might also use a video taken using a cell phone to keep track of attendance. The suggested method improves upon the state-of-the-art to the extent that it achieves an accuracy of 97.34 percent, sensitivity of 98.34 percent, recall of 97.23 percent, and an F1 score of 98.23 percent.