Masked face recognition

Biometric security is a type of security that verifies people's physical or behavioural features to identify them. One of them being face recognition, which is a technology that is capable of matching human faces to a database of faces. There are several existing deep learning models used for f...

Full description

Saved in:
Bibliographic Details
Main Author: Sim, Song Qin
Other Authors: Lin Weisi
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/153275
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Biometric security is a type of security that verifies people's physical or behavioural features to identify them. One of them being face recognition, which is a technology that is capable of matching human faces to a database of faces. There are several existing deep learning models used for face recognition. In this project, we are going to develop an alternative approach to this task. We will build our model based on a state-of-the-art model, and apply the attention mechanism. The accuracy of our model will be compared with existing face recognition models to evaluate its effectiveness.