Automatic Students Attendance Marking System Using Image Processing And Machine Learning

TLDR: The proposed system automatically records the student’s attendance during lecture hours using facial recognition technology with image processing instead of the traditional manual methods, and experimentation shows that it provides better accuracy than the existing PCA and other techniques.

Abstract: To track student attendance, colleges and schools use traditional methods involving manual marking on sheets. These methods are timeconsuming and tedious for teachers. The proposed system automatically records the student’s attendance during lecture hours using facial recognition technology with image processing instead of the traditional manual methods. The proposed system works in a controlled environment, in which students, face images are captured and then upon recognition, their attendance is automatically marked in an Excel sheet. Student’s face is detected using the Viola-Jones technique, whereas Linear Discriminate Analysis (LDA) along with KNN and SVM is used for face recognition. Experimentation shows that it provides better accuracy than the existing PCA and other techniques.