This Deep Learning Web Application utilizes a Convolutional Neural Network to process the person Images and predict if their Mask is ON/OFF accuracy of nearly 98%. Here this model is made by a pretrained model VGG16.
As Social Distancing is only tool to prevent COVID-19 wearing face masks is compulsory. To monitor the mass no of people whether they wear a mask or not I came up with a solution using deep learning Here I can used Convulutional Nueral Networks(CNN) to predict whether the person is wearing the mask or not . I took the person images with and with_out masks through web scraping and started working on it. the dataset consists of nearly 2000.
Our Model performs fairly well with an accuracy of 98% and an F1 Score of 97%. This provides a handy tool to utilize the power of Machine Learning and Artificial Intelligence in Binary Classification Problems where time and accuracy is the paramount objective of classification.
- Drop a ⭐ on the Github Repository.
- Clone the Repo by going to your local Git Client and pushing in the command:
https://github.com/ksdkamesh99/Face-Mask-Detection.git- Install the Packages:
pip install -r requirements.txt- At last, push in the command:
python app.py-
Go to
http://127.0.0.1:5000/and enjoy the application. -
Examples are provided in the directory You can try using them.
-
Some screenshots of the application are mentioned Below.
-
Home Page.
-
About Page.
-
Predictions Page/Result Page.
i. Narendra Modi With Mask.
ii. Donald Trump without Mask.
1 . To convert the application to asyncronous way by using ajax call.
2 . To deploy the application in AWS/GCP Platform for beter reach.
For any kind of suggesstions/ help in model code Please mail me at ksdkamesh99@gmail.com.