Masked Face Recognition using Deep Learning and MlOps

Parapurath Govindarajan, Akash (2022) Masked Face Recognition using Deep Learning and MlOps. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Facial recognition is a method of recognizing or verifying a person’s identification by looking at their face. Identifying the person while wearing a mask is more important in this pandemic situation. In this paper, we proposed the use of a Deep Learning algorithm to extract the feature therefore it helps to identify the person behind the mask. This will improve security even in this pandemic situation. A Deep Learning Neural Network or DNN, a widely used image processing algorithm, which is implemented to recognise the masked person. Moreover, Azure Ml is a cloud service which is used to implement the MLOps technology in our end to end application. This project is developed end to end with Flask and the process is automated with the help of Azure Machine Learning. Through this we developed an automated lifecycle for our Masked face identification model. We achieved an accuracy of 91% in recognizing a person.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	01 Dec 2022 17:30
Last Modified:	08 Mar 2023 14:47
URI:	https://norma.ncirl.ie/id/eprint/5954

Actions (login required)

View Item