Title: Face Recognition Algorithm and Newest Improvements of YOLO11 Model
Authors: Phuong Thao Cao, Nhat Nam D??ng, Minh Tri Nguyen
Volume: 8
Issue: 10
Pages: 13-24
Publication Date: 2024/10/28
Abstract:
Face Recogintion is a technology that stores images in the form of faceprint data, allowing the authentication of a person's identity. Facial recognition is applied in many different fields such as security, sales, healthcare, etc. In the first part of the paper, the general steps of the algorithm are introduced. At the same time, the parameters of the algorithm are studied. Face recognition is an algorithm could be affected by various factors that reduce the accuracy. We also study these factors and how to overcome them with data augmentation techniques. In the last part of the paper, we specifically study the algorithm through the YOLO11 newest model. YOLO11 uses convolutional neural networks (CNNs) for object detection, recognition, and classification. YOLO11 is created from the combination of convolutional layers and connected layers. In which, convolutional layers will extract the features of the image, and fully-connected layers will predict the probability and coordinates of the object. This is a model has fast processing speed, suitable for real-time applications.