https://github.com/abdulfatir/pyanpd

Automatic Number Plate Detection for Python using OpenCV
https://github.com/abdulfatir/pyanpd

Last synced: 5 months ago
JSON representation

Automatic Number Plate Detection for Python using OpenCV

• Host: GitHub
• URL: https://github.com/abdulfatir/pyanpd
• Owner: abdulfatir
• Created: 2016-06-06T10:03:27.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2018-11-29T13:25:04.000Z (almost 7 years ago)
• Last Synced: 2025-03-30T14:51:10.151Z (6 months ago)
• Language: Python
• Homepage:
• Size: 4.62 MB
• Stars: 66
• Watchers: 8
• Forks: 35
• Open Issues: 9
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# pyANPD

pyANPD is a high recall automatic number plate detector based on [this Stack Overflow answer](http://stackoverflow.com/a/37523538/2605733). For details of the algorithm, check the answer on Stack Overflow. The detector is robust to orientation. The precision decreases and recall increases if the `edge_density` threshold is decreased.

## Dependencies

1. [OpenCV](http://opencv.org/downloads.html)

2. [Numpy](http://www.numpy.org/)

## Usage

`python pyANPR.py `

This outputs an image with the same name with `-detected` appended.

### How to tweak it for your dataset?

Change `aspect_ratio_range` (Range of Aspect Ratio for Accepted Rectangles), `area_range` (Range of Area for Accepted Rectangles), and `se_shape` (Shape of Structuring Element for Morphological Closing) to the taste of your own dataset.

## Results

![1](https://raw.githubusercontent.com/abdulfatir/pyANPD/master/tests/2-detected.png)

![2](https://raw.githubusercontent.com/abdulfatir/pyANPD/master/tests/4-detected.png)

![3](https://raw.githubusercontent.com/abdulfatir/pyANPD/master/tests/3-detected.png)