https://github.com/ibz-04/number-plate-recognition

Vehicle number plate recognition using computer vision and image processing
https://github.com/ibz-04/number-plate-recognition

computer-vision easyocr matplotlib-python numpy object-detection opencv

Last synced: 18 days ago
JSON representation

Vehicle number plate recognition using computer vision and image processing

• Host: GitHub
• URL: https://github.com/ibz-04/number-plate-recognition
• Owner: iBz-04
• Created: 2024-10-17T09:46:42.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-10-18T09:01:28.000Z (29 days ago)
• Last Synced: 2024-10-20T21:53:50.990Z (27 days ago)
• Topics: computer-vision, easyocr, matplotlib-python, numpy, object-detection, opencv
• Language: Python
• Homepage:
• Size: 261 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# License Plate Detection and Recognition System

- This project demonstrates how to detect and recognize license plates from an image using Python Image Processing.

- It is a practical implementation of computer vision and OCR techniques, suitable for applications such as vehicle monitoring systems or parking management.

- it only works for images

## IMAGES 

### Processed Image



### Number plate extraction



### Final output



### Image Processing Workflow

1. **Reading the Image**: The input image is read using OpenCV, and then it's displayed using `matplotlib` for visualization.

2. **Grayscale Conversion**: The image is converted to grayscale to simplify processing, focusing on intensity rather than color.

3. **Noise Reduction**: A bilateral filter is applied to reduce noise while preserving the edges, preparing the image for edge detection.

4. **Edge Detection**: The Canny edge detection algorithm is used to identify edges, highlighting the boundaries of objects like the license plate.

5. **Finding Contours**: The system identifies contours (closed shapes) in the image, filtering out the most relevant contours that are likely to be the license plate.

6. **Approximating License Plate**: A polygon approximation is used to detect a quadrilateral contour, assuming the license plate is rectangular.

7. **Masking and Cropping**: The license plate area is isolated from the image, and the region is cropped for OCR.

8. **Text Recognition**: EasyOCR is used to extract text from the cropped license plate image.

## Installation

Installing dependencies:

```bash

pip install easyocr

pip install imutils

pip install opencv-python

pip install matplotlib

```