https://github.com/hamzaezzra/mlpdr
Moroccan license plate detection & recognition. Built with YOLOv3 and PyQt.
https://github.com/hamzaezzra/mlpdr
anpr dataset machine-learning moroccan-license-plates plate-detection plate-recognition python yolov3
Last synced: 10 months ago
JSON representation
Moroccan license plate detection & recognition. Built with YOLOv3 and PyQt.
- Host: GitHub
- URL: https://github.com/hamzaezzra/mlpdr
- Owner: HamzaEzzRa
- License: mit
- Created: 2021-06-04T18:32:50.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2023-11-14T20:53:24.000Z (over 2 years ago)
- Last Synced: 2025-05-12T21:38:03.761Z (about 1 year ago)
- Topics: anpr, dataset, machine-learning, moroccan-license-plates, plate-detection, plate-recognition, python, yolov3
- Language: Python
- Homepage:
- Size: 16.1 MB
- Stars: 20
- Watchers: 2
- Forks: 12
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MLPDR
### About
Moroccan license plate detection & recognition. Built with YOLOv3 and PyQt. + FLASK
### Setup
Install [Python](https://www.python.org/downloads/) Use Python 3.8.
Clone this repository, cd to its directory and run the following commands:
```
# Create and activate a new virtual environment
$ python -m venv env
## Windows
$ ./env/Scripts/activate
## Linux
$ source ./env/bin/activate
# Install the project's requirements
$ pip install -r ./requirements.txt
```
Before running the project, you will need the trained weights. Considering the size of the weights and that Git LFS has a monthly limit on bandwidth, you will have to download the latest [release](https://github.com/HamzaEzzRa/MLPDR/releases/tag/v1.0.0-beta) and copy the weights folder to the cloned project.
```
# Run the project
$ python ./main.py
$ python ./api.py # to run the API
$ python ./client.py # client side code to send the picture
```
### Screenshots
### Dataset
The network has been trained on the Moroccan license plate dataset: [https://msda.um6p.ma/msda_datasets](https://msda.um6p.ma/msda_datasets).