You are on page 1of 14

CONTENTS

 ABSTRACT
 INTRODUCTION
 SYSTEM ANALYSIS
 SYSTEM ARCHITECTURE
 LITERATURE SURVEY
 SYSTEM REQUIREMENTS
 CONCLUSION
 REFERENCES
ABSTRACT

The purpose of the project “Face Mask Detection Using Machine


Learning” is to create a tool that identifies the image of a human
that can calculate the probability that he/she wearing a mask or
not. Due to COVID, wearing a face mask is must in order to stay
safe. As the country starts going through various stages of
reopening, face masks have become an important element of our
daily lives to stay safe. Wearing face masks will be required in
order to socialize or conduct business. So, this application utilizes a
camera to detect if a person is wearing a mask or not.
INTRODUCTION

 Technologies in fields like machine learning and Artificial


Intelligence have Made our lives easier and Provide
Solutions to Several Complex Problems in Various Areas.
 This Model helps in Reduce the Man Power and will
Recognize the Masked and Non-masked People through
live Video stream .
 Where there is overly crowded places like Educational
Institutions ,Shopping malls, Companies, etc…..
SYSTEM ANALYSIS

 EXISTING SYSTEM:

In this System, if a person wears face mask Improperly by not


Covering nose even though it will get the best output Results.
This Paper Reproduced the training and testing of the most
used classical Machine Learning Model techniques with Open cv
tensor flow and keras.
DRAWBACKS OF EXISTING SYSTEM

 Errors and Inconsistency : It is virtually impossible for a human


being to be accurate and perfect all the time.

 Time Consuming : Searching a record of a particular consumer


from a big far registers is certainly a very time consuming and
tedious task. This is because the search requires the managers to
go through all the registers/ledgers and search the particular record
from a set of 500 to 1000 records or even much more than that.

 Lack of security : we collect the every user details is difficult to store


PROPOSED SYSTEM

We propose a two-stage CNN Algorithm ,where the first stage

detects Human faces, while the Second stage uses a lightweight

image classifier to classify the faces detected in the first stage as

either ‘Mask’ or ‘No Mask’ Faces and draws bounding boxes around

them along with the detected Class name. By using imutils we can

integrate live video cam to detect the with or without masks persons.
ADVANTAGES OF PROPOSED SYSTEM

 Intelligent Alerts.

 Facial Recognition.

 Easy Implementation.

 Staff Friendly.

 No New Hardware Needed.


SYSTEM ARCHITECTURE
MODULES:
• Data Visualisation
• Splitting the data
• Building the Model
• Training the CNN model
• Labelling the Information
• Importing and Detecting the Faces with and Without Mask
SYSTEM REQUIREMENTS
HARDWARE REQUIREMENTS
 SYSTEM : I5
 HARD DISK : 500GB
 RAM : 8GB

SOFTWARE REQUIREMENTS
 OPERATING SYSTEMS : windows10
 CODING LANGUAGE : python
 TOOL : vs code
 DATABASE : Dataset
CONCLUSION

In this work, the Face Net pre-trained model has been used for
improving masked face recognition. We have benchmarked this
approach with two well-known datasets and our dataset. Our approach
tested on these datasets shows better recognition rates. So Face Net
model trained on masked and non-masked images gives better accuracy
for simple masked face recognition. Although we concentrated on masks
induced by a hat, sunglasses, beard, long hairs, mustache, and medical
mask, our methodology can still be extended to more complex and many
other sources of occlusion. Obviously, this method may not be
appeasement for all types of masks. Further, the more accurate and
sophisticated approach may than be needed. In later work, it is our
importance to enhance and enlarge our work to address different
extreme masks condition of face recognition.
REFERENCE
1. Roomi , Parisa “A Review Of Face Recognition
Methods,” in International Journal of Pattern
Recognition and Artificial Intelligence, 2013,
27(04), p.1356005

2. A. S. Syed navaz, t. Dhevi sri, Pratap mazumder, “


Face recognition using principal component
analysis and neural network,” in International
Journal of Computer Networking, Wireless and
Mobile Communications (IJCNWMC), vol. 3, pp.
245-256, Mar. 2013.
ANY QUERIES!

You might also like