This project aims to develop an Automatic Number Plate Recognition (ANPR) system for Indian Number plates using YOLO (You Only Look Once) object detection algorithm and Streamlit web application framework.
- Clone the repository:
git clone https://github.com/harshrai1023/Automatic-Number-Plate-Recognition-ANPR-Yolo-Streamlit.git
- Install the required dependencies:
pip install -r requirements.txt
- The pre-trained YOLO weights file can be found in the
models
directory. Run the following before they can be used in the environment
pip install git+https://github.com/sberbank-ai/Real-ESRGAN.git
- Run the Streamlit app:
streamlit run app.py
-
Open your web browser and navigate to
http://localhost:8501
. -
Upload an image containing number plates.
-
Click the "Detect" button to start the ANPR process.
The dataset used for the training the YOLOv8 model is License Plate Recognition Image Dataset - resized640_aug3x-ACCURATE and can be downloaded from the Roboflow website here.