🇻🇳 Vietnamese License Plate Recognition - CS117.O21.KHTN

Teacher Instruction

• PhD. Ngo Duc Thanh

Team

No.	Full name	Student ID	Email	Github
1	Trần Như Cẩm Nguyên	22520004	22520004@gm.uit.edu.vn	cnmeow
2	Trần Thị Cẩm Giang	22520361	22520361@gm.uit.edu.vn	Yangchann
3	Nguyễn Hữu Hoàng Long	22520817	22520817@gm.uit.edu.vn	EbisuRyu
4	Trần Minh Quân	22521191	22521191@gm.uit.edu.vn	Be-Tap-Code

Introduction

This project aims to build a web application for recognizing Vietnamese license plates, using efficient deep-learning algorithms for accurate and rapid recognition. This system can work on 2 types of license plate in Vietnam, 1 line plates and 2 lines plates.

Features

• Detect license plates in images
• Recognize characters on Vietnamese license plates
• User-friendly web interface
• High accuracy and performance

Algorithm

Installation

• Clone the repository:

  git clone https://github.com/cnmeow/Vietnamese-License-Plate-Recognition.git
  cd Vietnamese-License-Plate-Recognition

• Install the required dependencies:

  pip install -r requirements.txt

• Pretrained model provided in model folder

• Download yolov5 from this link:** yolov5 - Google Drive

• Copy yolov5 folder to project folder

Inference

Web application

• Run the web server:

python main.py

• Open your web browser and go to localhost:4000.

  

• Click Choose File button, select the image of the license plate you want to recognize

• Click the Upload and Recognize button to process the recognition.

On image

python lp_image.py -i test_image/3.jpg

On webcam

python webcam.py

Training

Training code for Yolov5:

Use code in training folder

  training/Plate_detection.ipynb     #for LP_Detection
  training/Letter_detection.ipynb    #for Letter_detection

References

• trungdinh22
• License Plate Detection Dataset
• Character Detection Dataset
• Mì Ai
• winter2897