What type of study is this?

This is a Literature Review study.

September 10, 2025

A Comprehensive Review Concerning the Involvement of Artificial Intelligence Techniques in Face Recognition System

Key Points

The review shows that deep learning models achieve state-of-the-art accuracy in face recognition, particularly through frameworks like FaceNet.
Key methodologies include traditional techniques, machine learning approaches, and deep learning models, emphasizing the evolution in face recognition systems.
Traditional methods like Eigenfaces laid the groundwork, while modern approaches leverage machine learning and deep learning for improved performance.
Future directions for face recognition systems emphasize explainable AI, fairness, and scalable architectures to enhance technology applicability.

Abstract

This paper surveys the key methodologies used in the field of Face Recognition Systems, categorizing them into traditional techniques, machine learning approaches, deep learning models, and hybrid systems. Traditional methods such as Eigenfaces and Fisherfaces laid the foundation for face recognition by utilizing linear projection techniques. Machine learning methods like Support Vector Machines (SVM) and Random Forests have improved performance, particularly in scenarios with smaller datasets. The advent of deep learning has marked a significant turning point, with models like Convolutional Neural Networks (CNNs) and frameworks such as FaceNet and DeepFace achieving state-of-the-art accuracy and robustness across varying conditions, including illumination, occlusions, and facial expressions. Future directions discussed in this paper include advancements in explainable AI, fairness, federated learning, and scalable architectures to address these challenges while improving the robustness and scalability of face recognition systems.

AI에게 질문

Bookmark