Bunk Alert System Based on Convolutional Neural-Network in Real-Time

Nowadays, students find it easy to bunk lectures in college unnecessarily. As a result, to stop and to decrease them we have decided to build a system which will detect their faces. The system is composed of five main steps: face segmentation, facial features detection, face alignment, embedding, and classification. We are using deep learning methods for the fiducial points extraction and embedding. Support Vector Machine (SVM) is used for classification. This system is capable to run in real-time therefore it is easy to send an email alert with the students name to the HOD and the student so that the student will get to know he/she is bunking the lectures and the camera captured him/her The warning email will help students to attend lectures and hence it will decrease the most concerned problem i.e. Bunking Lectures. This System is based on Face Detection Algorithm and the details of the system will be shared totally throughout this paper with the comparative study of other similar algorithms.