Iranian License Plate Recognition Using a Reliable Deep Learning Approach

TL;DR

This paper presents a reliable deep learning approach for Iranian license plate recognition, combining YOLOv4-tiny for detection and CRNN with CTC for character recognition, addressing challenges like weather and lighting conditions.

Contribution

It introduces a two-step method using YOLOv4-tiny and CRNN with CTC for efficient license plate detection and recognition in Iranian plates, handling various environmental challenges.

Findings

High detection accuracy with YOLOv4-tiny.

Effective character recognition using CRNN and CTC.

No need for character segmentation or labeling.

Abstract

The issue of Automatic License Plate Recognition (ALPR) has been one of the most challenging issues in recent years. Weather conditions, camera angle of view, lighting conditions, different characters written on license plates, and many other factors are among the challenges for the issue of ALPR. Given the advances that have been made in recent years in the field of deep neural networks, some types of neural networks and models based on them can be used to perform the task of Iranian license plate recognition. In the proposed method presented in this paper, the license plate recognition is done in two steps. The first step is to detect the rectangles of the license plates from the input image. In the second step, these license plates are cropped from the image and their characters are recognized. For the first step, 3065 images including license plates and for the second step, 3364 images including characters of license plates have been prepared and considered as the desired datasets. In the first step, license plates are detected using the YOLOv4-tiny model, which is based on Convolutional Neural Network (CNN). In the next step, the characters of these license plates are recognized using Convolutional Recurrent Neural Network (CRNN), and Connectionist Temporal Classification (CTC). In the second step, there is no need to segment and label the characters separately, only one string of numbers and letters is enough for the labels.