Our project is Gate Access Aontroller: A gate is open for specific cars based on their plate number, by capturing photographic images from license plates and transform the optical data into digital information and take a decision.
- Take input (image or video).
- Applying Edge Detection.
- Binarization.
- Filteration and Extraction.
- Check whether there is any License Plate or not
- If Yes: do morphological processing, if No: take new input
- License Plate Recognition and compare with database
- If License Plate matched open the gate if not do nothing
- Thresholding
- Segmentation
- Smoothing
- Template matching
This is an list of needed instructions to set up your project locally, to get a local copy up and running follow these instructuins.
- Clone the repository
$ git clone git@github.com:MoazHassan2022/License-Plate-Recognition.git -
Navigate to repository directory
$ cd License-Plate-Recognition/ -
Install dependencies
$ pip install numpy$ pip install PyQt5$ pip install opencv-python$ python -m pip install -U scikit-image$ pip install imutils$ python -m pip install -U matplotlib
- Open IDE that supports python(recommended: Pycharm)
- Do not forget to install the required packgaes & libraries
- Run the application.py
- Open the terminal and the following code
$ cd Jupyter && jupyter notebook
- Install QT tools
$pip install pyqt5-tools
- Start the designer
$designer
-
Results and analysis regarding the plate detection
We managed to detect the plate from 62 images out of 66 images
success rate =94%. -
Results and analysis regarding characters recognition
37 error images from 80 images
The success rate = 53.75%. -
Overall results
The success rate = 43.54%.
