Face Recognition from Video using Deep Learning

Face recognition (FR) and verification is the immeasurable technology to encounter any criminal activities nowadays. With the remarkable applications extending from criminal ID, security, and observation to amusement sites. This system (recognition of faces) is exceptionally helpful in banks, air terminals, and different associations for screening customers. In deep learning, convolutional neural networks (CNN) have gained attention for face recognition but to train CNN requires more data, which is very difficult in case of applications like criminal activities (robbery, murder, etc). Therefore, this paper proposed a face recognition system that makes searching for criminals easy and quick with less time and hence efficiently helps police and administration. In this paper, a pretrained model i.e FaceNet (FN) is used for face recognition from video. FN modifies the face images into a close-packed Euclidean space where separations extent the face nearness.