FACIAL ATTENDANCE SYSTEM USING MTCNN AND FEATURE MAPPING

Artificial intelligence and Computer Vision are some of the fields which have shown rapid growth in recent years. These technologies have greatly reduced the effort we used to put in our day to day work and facial detection and Recognition are such revolutionary technologies. While many approaches are possible, on base, this technology works by recognizing the features of an individual face and matches it with the data which is stored in the database. Face is the representation of one’s identity. Hence, we have proposed a full-fledged automated attendance system based on facial detection and recognition. Smart Attendance using Real-Time Face Recognition is a real-world solution which comes with day to day activities capable of handling everyday student / employee attendance systems. Using feature mapping, this system is capable of detecting multiple faces, saving the facial features using feature mapping and at last recognition based on the database. The Computer vision will be able to find and recognize human faces fast and precisely in images or videos that are being captured through a surveillance camera or webcam. Numerous algorithms and techniques have been developed for improving the performance of face recognition but to get the best results we have created a compounded deep learning model. Directly streaming the live video, faces will be detected, mapped and recognized and automatically saved into the database with the date and time of entry. Later the authorities can easily check the database for the complete information. Improving upon the existing systems and creating a more robust model for better and more efficient processes. Keywords— Artificial Intelligence, Facial Recognition, Facial Detection, Multi-task Cascade Convolutional Neural Network (MTCNN), Facial Feature Mapping, Deep Learning, Computer Vision