Practical:12 MINI PROJECT – FACE MASK DETECTION

 INTRODUCTION

The world is fighting against the health crisis named Covid-19. This virus is killing people on large scale and the cases increases as days passes. Because of this virus, people had forgotten to live a normal life. The impact of this virus and its consequence are felt differently depending on the symptoms they have. There were many symptoms of coronavirus such as fever, sneezing, coughing, etc. There are many precautions as social distancing, wearing a mask, use of sanitizers, etc. The important is to wear a face mask whenever you are in the public or around the crowd. The virus spreads through to a close contacts. The rules and laws are made by the government as an action to the increase of cases and deaths in many areas.

Reports indicate the wearing a facemask while it works reduces the risk of transmission. A hybrid model using deep learning and classical machine learning for face mask detection has been presented. A face mask detection dataset contains a mask image and without a mask image by using OpenCV we are going to do face detection from the image in the dataset and also video stream. We will use python, OpenCV, Tensor Flow, and Keras. Our goal is to identify whether the person on the image or video is wearing a mask or not with the help of Computer vision and deep learning. We will proceed two more Python script used to

1. Detect a person has face mask in image.
2. Detect a person has face mask in video stream

TECHNIQUES USED

1. Tensorflow
It is an open source library which we will use to train and test the model of our project.

2. Keras
It is an easy to use open source library for developing deep neural network.

3. OpenCV
We will use OpenCV to analysis the images and video if people are wearing the mask or not through face detection.

4. CNN Architecture.
It is use for the classification of the images and train the model.

Dataset

To test and train the model we have simply taken the dataset of 25 images of mask and 25 images of no mask.

System Design

Firstly, we will implement the project in python using Google Colab. The techniques we use in this project is OpenCV, Deep Learning and also some python libraries like TensorFlow, Keras, imutils, Numpy, Matplotlib and Scipy. We have use MobileNetV2 architecture and CNN algorithm for model as it can get high and low computation scenarios.

Implementation



Project is divided into 4 modules:

1.Dataset Collecting: We collect the data of wearing mask and not wearing mask and find the accuracy of dataset.

2.Dataset Extracting: Using MobilenetV2 we will extract the features of mask and no mask sets.

3.Training model: We will train the model using Keras, Python library and OpenCV.

4.Face Mask Detection: Lastly, we will detect the mask or not mask in images and live video stream.


Functionality

The major function of our project is to detect whether the person is wearing a mask or not. If the person is not wearing mask we can send the message to them to wear the mask. It is useful at various places like airport, railway station, offices, hospitals, schools and many more places which are always crowded.

Expected Outcome:

Reference link: https://github.com/Riya2112/DS_Practicals/tree/main/Practical12

Thank you:)


Comments

Post a Comment

Popular posts from this blog

18IT100_Practical_Exam_Work

Image
Task-1: Dataset Description using Orange tool. What is need to be done to improve the accuracy of the classification result of the given dataset? Get the maximum classification accuracy possible by performing the following methods. -->Pre-processing o Encoding o Normalization o Missing value handling o Feature Selection Compare your accuracy with and without applying pre-processing steps. Perform the Classification and visualize accuracy before and after preprocessing in Orange/Python. What is Data Pre-processing? In any Machine Learning process, Data Preprocessing is that step in which the data gets transformed, or Encoded, to bring it to such a state that now the machine can easily parse it. In other words, the features of the data can now be easily interpreted by the algorithm. Encoding Encoding is the process of converting data from one form to another. While "encoding" can be used as a verb, it is often used as a noun, and refers to a specific type of encoded data Nor...
Read more

Practical:10 Getting started with Neo4j and Gephi Tool

Image
This blog contains two different tools , Neo4j and Gephi tool for data visualization in graphical form . Neo4j Neo4j delivers the lightning-fast read and write performance you need, while still protecting your data integrity. It is the only enterprise-strength graph database that combines native graph storage, scalable architecture optimized for speed, and ACID compliance to ensure the predictability of relationship-based queries. In simple words, Neo4j is the MySQL of the graph databases. It provides a graph database management system, a language to query the database, a.k.a CYPHER, and a visual interface with the neo4j browser. Advantages of Neo4j Following are the advantages of Neo4j. Flexible data model − Neo4j provides a flexible simple and yet powerful data model, which can be easily changed according to the applications and industries. Real-time insights − Neo4j provides results based on real-time data. High availability − Neo4j is highly available for large enterprise real-time...
Read more

Practical:11 PREDICTING GENDER AND AGE USING IMAGE DATA IN PYTHON

Image
What is OpenCV? OpenCV is short for Open Source Computer Vision. Intuitively by the name, it is an open-source Computer Vision and Machine Learning library. This library is capable of processing real-time image and video while also boasting analytical capabilities. It supports the Deep Learning frameworks TensorFlow, Caffe, and PyTorch. What is a CNN? A Convolutional Neural Network is a deep neural network (DNN) widely used for the purposes of image recognition and processing and NLP. Also known as a ConvNet, a CNN has input and output layers, and multiple hidden layers, many of which are convolutional. In a way, CNNs are regularized multilayer perceptrons. Age and gender, two of the key facial attributes, play a very foundational role in social interactions, making age and gender estimation from a single face image an important task in intelligent applications, such as access control, human-computer interaction, law enforcement, marketing intelligence and visual surveillance, etc. Her...
Read more