Facial Recognition Based on Machine and Deep Learning
Assia Ould Hamou, Fatma Zohra Chelali · 2024
Facial recognition technology plays a crucial role in enhancing security measures, providing accurate identification and authentication of individuals, thereby reducing the risk of unauthorized access and fraudulent activities. In this paper we propose an implementation of face recognition system using three datasets under uniform and complex background: Olivetti Research Laboratory (ORL), Computer Vison (CV) and Georgia Tech face database (Gt_Db). The system utilizes various machine and deep learning methods, including the Local Directional Texture Pattern (LDTP) and Median Ternary Pattern (MTP) descriptor characterization, followed by Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) classification. Additionally, a Convolutional Neural Network (CNN) was trained and implemented. The results were highly satisfactory, achieving a recognition rate of 100% under a uniform background and 98.57% under a complex background.