This project combines YOLOv5, a real-time object detection model, with a Flask web application for number plate recognition. The dataset is annotated using LabelImg, and the app is run using app.py
.
Ensure you have the following installed:
- Python 3.x
- PyTorch
- OpenCV
- YOLOv5
- LabelImg
- Flask
YOLOv5 divides an image into a grid, predicting bounding boxes and class probabilities for objects. Designed for real-time object detection.
LabelImg streamlines manual annotation for object detection. Annotations are saved in YOLO format.
Feed annotated data into YOLOv5. The model adjusts parameters for accurate predictions. Trained weights are saved for later inference.
The Flask app (app.py
) runs inference on new images using the trained YOLOv5 model.