Facial recognition for passport check

Abstract

This thesis explores the implementation and evaluation of deep learning models for facial recognition in the context of passport checks. Key components include VGGFace, MTCNN, LBP, and Siamese Neural Networks. The research compares the performance of these models with state-of-the-art approaches using the LFW dataset. Challenges such as dataset availability, overfitting, and computational resources are addressed. The findings highlight the effectiveness of the models for passport check applications and the need for further research in addressing challenges related to aging, lighting variations, and dataset biases. The outcomes contribute to improving identity verification processes and enhancing passport control and border security systems.