Multi-String Missing Characters Restoration for Automatic License Plate Recognition System

Developing a license plate recognition system that can cope with unconstrained real-time scenarios is very challenging. Additional cues, such as the color and dimensions of the plate, and font of the text, can be useful in improving the system's accuracy. This paper presents a deep learning-based plate recognition system that can take advantage of the bilingual text in the license plates, as used in many countries, including Saudi Arabia. We train and test the model using a custom dataset generated from real-time traffic videos in Saudi Arabia. Using the English alphanumeric alone, the accuracy of our system was on par with the existing state-of-the-art algorithms. However, it increased significantly when the additional information from the detection of Arabic text was utilized. We propose a new algorithm to restore noise-affected missing or misidentified characters in the plate. We generated a new test dataset of license plates to test how the proposed system performs in challenging scenarios. The results show a clear advantage of the proposed system over several commercially available solutions, including Open ALPR, Plate Recognizer, and Sighthound.

@article{KHAN2023,
  title     = {Multi-String Missing Characters Restoration for Automatic License Plate Recognition System},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {14},
  number    = {3},
  year      = {2023},
  publisher = {The Science and Information Organization},
  author    = {Ishtiaq Rasool KHAN and Syed Talha Abid ALI and Asif SIDDIQ and Seong-O SHIM},
  doi       = {10.14569/IJACSA.2023.0140395},
  url       = {https://doi.org/10.14569/IJACSA.2023.0140395}
}