An OpenCV-based implementation of License Plate Recognition.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

License Plate Recognition using OpenCV.

This is an OpenCV-based implementation of License Plate Recognition. For more details on OpenCV please check here.

Setup and Execution

To run this code you will need to install opencv dependencies:

The following steps have been tested for Ubuntu_16.10:

  • Essentials
    • [compiler] $sudo apt-get install build-essential
    • [required] $sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
    • [optional] $sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev

Getting the source code

$ cd ~/<my_working_directory>
$ git clone
$ git clone

Compilation from Source

  • Enter into your /opencv folder
  • $mkdir build
  • $cd build
  • $cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ..
  • wait for a while and when there are no errors:
  • $make -j7
  • $sudo make install

Running the code

Compilation: Please use the CMakeLists.txt file in the src folder.

  • use cmake-gui to set the source to src and a build folder
  • then run make from the /build folder


This project is a fork out of an academic project that I worked on as part of my studies at TU Berlin.

  • A big thanks to Dr. Ahmed Elhossini who was our mentor during this project
  • This project was inspired by the Masters thesis "FPGA Implementation of License Plate Detection and Recognition" by Farid Rosli.

Known Issues

  1. It's not yet possible to split the source code into separate modules since CMake considers only one source file per folder.
  2. The database is not optimal as it's just a trial.


This project is licensed under GPLv3. Please check the license file for details.