Masked face detection system using google firebase

Azman, Anis Zahirah (2021) Masked face detection system using google firebase. Masters thesis, Universiti Tun Hussein Malaysia.


Download (1MB) | Preview
[img] Text (Copyright Declaration)
Restricted to Repository staff only

Download (1MB) | Request a copy
[img] Text (Full Text)
Restricted to Registered users only

Download (1MB) | Request a copy


The global health epidemic caused by the breakout of a coronavirus disease in 2019 (COVID-19) has had a significant impact on way we view our environment and live our daily lives. The number of people infected with Covid-19 is rapidly increasing. As a result, several countries are facing economic disasters, recession, and other problems. Separating ourselves from society, remaining at home, and detaching ourselves from the outside world is one thing we should do. But that is no longer an option; people must work to exist, and no one can live in their homes eternally. People should wear masks and maintain social distance as a precaution. As a result, detecting face masks has become a critical responsibility in assisting the global community. This report describes a simplified method for accomplishing this goal utilizing TensorFlow, Keras, OpenCV, and Convolutional Neural Networks, as well as some basic Machine Learning packages. The suggested approach successfully recognizes the face in a picture and then determines whether it is covered by a mask. If a person is discovered without a face mask, an alert warning is issued, and the person's face is captured. In addition, the value of masking and unmasking faces is saved in the cloud for future use. By using this deep learning, enable the system to be faster and more precise to detect the faces and as a result, the accuracy of mask and unmask faces detection is higher than 90%. As all the facilities open and the number of COVID-19 cases continues to rise across the country, everyone must adhere to the safety precautions until the outbreak is over. As a result, this module assist in recognizing people wearing masks when entering premises.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering
Depositing User: Mrs. Sabarina Che Mat
Date Deposited: 18 Apr 2022 01:53
Last Modified: 18 Apr 2022 01:53

Actions (login required)

View Item View Item