On an Empirical Study: Face Recognition using Machine Learning and Deep Learning Techniques

Face recognition is an interesting topic in biometrics research, which can be divided into two sub-problems: face detection followed by face recognition. The application of face recognition in real life situations and pose variations still remains a challenge. The aim of this paper is to evaluate and compare various systems of face recognition based on speed and high accuracy Machine Learning algorithms. The Support Vectors Machine is a strong algorithm for mutli-classification. The feed- forward Neural Network is a popular one. Recently, Deep Learning is becoming a very important subset of machine learning due to its high level of performance across many types of data, in particular using Convolutional Neural Networks (CNNs). A large colored Face Database is used to evaluate these three proposed and adapted architectures. The results are competitive.