Deep Learning-Based Bangladeshi License Plate Recognition System

摘要

A License Plate Recognition (LPR) is a technique to automatically identify and recognize the license plate of a vehicle. In today’s world where we want to do everything in no time, automated LPR has opened a new door in Intelligent Traffic System. With the help of ALPR, we can implement many smart systems starting from a parking facility to crime investigation. For effective License Plate Recognition, accurate License Plate Detection and License Plate Segmentation are crucial. Many existing algorithms are using different image processing and machine learning techniques for detection, segmentation, and recognition. These algorithms are highly computational extensive and somewhat unreliable. In our paper, we have proposed an end- to-end license plate recognition system for Bangladeshi vehicles. We have divided our system into three different phases. The first phase is license plate detection and localization. For that, we have used YOLOv3. In the second phase, we have implemented a custom segmentation algorithm specifically for Bangladeshi license plates which is robust and computationally fast. In the final phase, we have implemented a character recognition model with convolutional neural network (CNN). This recognition system has achieved 97.5% accuracy. Moreover, we have built a diversified dataset with 2000 images where we have tried to capture the environmental factors.