Real time facial recognition security system
Abstract
This system aims at detecting and identifying unknown faces in video footage. This is achieved by the system using a number of algorithms to match the identified face image with captured images in the database. Face recognition is technology used for recognizing human faces based on certain patterns and re-detect faces in various conditions. Various methods of face recognition have been developed
and increased accuracy in the main goal in the development of face recognition systems. FaceNet is one method in face recognition technology that uses MTCNN, Multi-task convolutional neural network, which combines face detection with face recognition, based on the cascade framework, this system can be
used to extract high-quality features from faces, called face embeddings, that can then be used to train a face recognition system. This method is based on a deep convolutional network and triplet loss training to carry out training data, but the training process requires complex computing and a long time. By integrating the Tensorflow learning machine and pre-trained model, the training time needed is much shorter.