https://github.com/dev-khant/car-number-plate-detection-and-extraction

Detection of Car number plate and extraction of number.
https://github.com/dev-khant/car-number-plate-detection-and-extraction

aws-textract docker flask heroku image-processing yolov4

Last synced: 25 days ago
JSON representation

Detection of Car number plate and extraction of number.

• Host: GitHub
• URL: https://github.com/dev-khant/car-number-plate-detection-and-extraction
• Owner: Dev-Khant
• Created: 2022-06-11T12:30:11.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2022-10-23T11:45:55.000Z (about 2 years ago)
• Last Synced: 2023-03-05T13:09:08.257Z (over 1 year ago)
• Topics: aws-textract, docker, flask, heroku, image-processing, yolov4
• Language: Jupyter Notebook
• Homepage:
• Size: 930 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Detect Car Number Plate & Extract the Number

This project is about detecting number plate of a car in an image and then extracting the number from the plate. 


**Tensorflow** and **OpenCV** are used for training model and for image processing.

## Model

Here model used for Object Detection is **YOLOv4** from DarkNet. Used **AWS Textract** for extracting number from cropped image. 


The accuracy achieved by YOLOv4 was **98.9%**.

## Deployment

**Flask** is used to develop Web App along with HTML and CSS. Have also used **Docker** to containerize flask app for deployment. 


Dockerized flask app can be deployed on **Heroku**, **AWS**, **Google Cloud**, or **Azure**.

➤ In main page first we upload the image.

![Screenshot 2022-07-13 092843](https://user-images.githubusercontent.com/57898986/178670670-2bafd8f5-83b0-49ed-8ff0-d25bd5cb3c88.png) 



➤ On clicking **Detect** image will processed and the number will be extracted.

![Screenshot 2022-07-13 092916](https://user-images.githubusercontent.com/57898986/178671427-b81ad3e4-419d-45a1-a270-7242503bf7d2.png)