https://github.com/aungkaungpyaepaing/mask-nomask-classification

Purpose of this project is to classified the captured image or input image, has masks or not. This model had trained with Convolutional Neural Network (CNN) and has high accuracy. The only problem of this model is it cannot detect the mask with different color due to dataset but included possible solution at the end of doc.
https://github.com/aungkaungpyaepaing/mask-nomask-classification

classification convolutional-neural-networks deep-learning deep-neural-networks image-classification image-processing

Last synced: 12 days ago
JSON representation

Purpose of this project is to classified the captured image or input image, has masks or not. This model had trained with Convolutional Neural Network (CNN) and has high accuracy. The only problem of this model is it cannot detect the mask with different color due to dataset but included possible solution at the end of doc.

• Host: GitHub
• URL: https://github.com/aungkaungpyaepaing/mask-nomask-classification
• Owner: aungkaungpyaepaing
• Created: 2024-03-25T04:05:05.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-03-25T05:13:27.000Z (10 months ago)
• Last Synced: 2024-11-20T20:58:08.472Z (2 months ago)
• Topics: classification, convolutional-neural-networks, deep-learning, deep-neural-networks, image-classification, image-processing
• Language: Jupyter Notebook
• Homepage:
• Size: 51 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Mask and No Mask Classifier


After watching the news about air pollution, just thought about making a Mask and No Mask Classification Model so that it can be used in different programs like Real-time detection programs in Hotel, Hospital, Classroom, Work, and so on...

This model is trained by Convolutional Neural Network and work pretty well based on the database.

Imported Packages 

- TensorFlow

- Numpy

- Matplotlib

- CV2

Model Evaluation

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/c3f56c71-f089-42d1-948b-1ef918f82cba)

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/7e04acbf-2c26-49d0-8e90-b309a63da345)

Model Performance 

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/bf70d840-c4df-41f2-9057-584b8530cfa6)

Testing Mask

Process 1

Input image

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/cc68d6ca-9496-4be5-ad77-6d43c6635b43)

Process 2

Pre-processing image

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/17f09e7b-ed4a-4466-b2da-c6786aacd80e)

Process 3 

Model Prediction and Result

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/8f4f72da-fdb8-401d-8f03-f7524ec9c5e8)

Process 4

No mask image input

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/fc4f0fca-76e9-4d2c-973e-47e1254c74a9)

Process 5 

Pre-processing Image

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/db06c0f0-7e87-48f4-8fe6-384fdd97da72)

Process 6

Model Prediction and Result

![image](https://github.com/aungkaungpyaepaing/Mask-NoMask-Classification/assets/88584127/741b6de3-291c-4bb9-b019-04ede8f9e270)

The dataset of this program is from here -> https://github.com/prajnasb/observations/tree/master/experiements/data

Problem Statement

Images that had used as a dataset doesn't include the masks with different colors. Although the model works well, the images that have been trained are with the masks with white color so the model sees the mask with different colors as no mask. 

Solution

Train the model with a dataset that includes every kind of desired mask.

Use image processing techniques to detect the mask or mask shape before doing classification.