Scribd
Upload
36 views28 pages

Mask Detector

The document introduces a mask detector app built using deep learning and Android. It discusses deep learning concepts and the Android platform. It then outlines the 6 steps to build the mask detector: 1) data gathering and preparation, 2) model creation, 3) model training, 4) model evaluation, 5) model deployment to Android, 6) final result of an app that can detect masks. Key technologies used include Python, Keras, TensorFlow, OpenCV and Java. The conclusion emphasizes the importance for Android developers to be familiar with multiple technologies.

Uploaded by

Ratik Tiwari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
36 views28 pages

Mask Detector

The document introduces a mask detector app built using deep learning and Android. It discusses deep learning concepts and the Android platform. It then outlines the 6 steps to build the mask detector: 1) data gathering and preparation, 2) model creation, 3) model training, 4) model evaluation, 5) model deployment to Android, 6) final result of an app that can detect masks. Key technologies used include Python, Keras, TensorFlow, OpenCV and Java. The conclusion emphasizes the importance for Android developers to be familiar with multiple technologies.

Uploaded by

Ratik Tiwari
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
You are on page 1/ 28

Greetings to all!

I am Ratik Tiwari
CSE – 5A
03913302718
ratiktiwari@[Link]
Mask Detector
using
Deep Learning & Android
Contents

◈ Deep Learning ……………………………………………..


◈ Android Development……………………………………...
◈ Mask Detector Process……………………………………
◈ Deployment in Android…………………………………….
◈ Final Result…………………………………………………
◈ Technologies Used………………………………………...
◈ Conclusion………………………………………………….
Intro to Deep Learning and
Android Development
Let’s have a look into what this stuff is…

1
“
Deep learning is an artificial intelligence (AI) function that
imitates the workings of the human brain in processing
data and creating patterns for use in decision making. Deep
learning is a subset of machine learning in artificial
intelligence that has networks capable of learning
unsupervised from data that is unstructured or unlabeled.

2
Deep Learning Process

1. Data Gathering 7. Deployment

2. Data Preparation 6. Model Evaluation

4. Model Training
3. Model Creation 5. Model Testing

3
What is Android?

◈ Android is an open source and Linux-


based Operating System for mobile devices
such as smartphones and tablet computers.
◈ Developed using Java and Kotlin officially.
◈ I’ve used Java Language to develop this app.

4
Mask Detector

5
Step - 1

Data Gathering and Preparation using Kaggle


Mask_Faces dataset, Scikit Learn and NumPy.

6
Place your screenshot here

7
Step – 2

Model Creation:
Our model comprises of two convolutional
layers, pooling layers and one fully connected
layer

8
Place your screenshot here

9
Step – 3

Model Training using Adam Optimizer which


uses Stochastic Gradient Descent

25% of Total Data is used for validation or


testing.

10
Place your screenshot here

11
Step – 4

Model Evaluation using Matplotlib plots

12
Place your screenshot here

13
Step – 5

Let’s do some prediction!!!

14
Place your screenshot here

15
Step – 6

Deployment of .tflite Model in Android

16
Place your screenshot here

17
Place your screenshot here

18
Place your screenshot here

19
Place your screenshot here

Final Result

Here, our app is ready to detect


masks!!!
20
Process of Deployment

Model Adding .tflite Capturing


conversion to to Android image and
.tflite Assets resizing it.

Drawing Getting Passing image


Rectangles predicted to .tflite
and Strings Label list model.

21
Technologies Used

◈ Python 3
◈ Keras with Tensorflow 2.0 as backend.
◈ OpenCV
◈ Java

22
Conclusion
In order to be an Android Developer, just one or two things are not
enough. One must be aware of different type of libraries, languages,
databases etc. in order to build a powerful and standardized project.

A good Android Developer is the one who really is aware of many


technologies, frameworks etc. as everything is interlinked.

23
Thank
You!

You might also like