Development of ANPR Framework for Pakistani Vehicle Number Plates Using Object Detection and OCR

Salma Salma,Adil Zulfiqar,Maham Saeed,Rauf Ur Rahim,Muhammad Gufran Khan,Muhammad Tahir Bhatti,Atila Bueno

doi:10.1155/2021/5597337

Salma Salma, Adil Zulfiqar + Show 5 more

Open Access

https://doi.org/10.1155/2021/5597337

Copy DOI

Abstract

The metropolis of the future demands an efficient Automatic Number Plate Recognition (ANPR) system. Since every region has a distinct number plate format and style, an unconstrained ANPR system is still not available. There is not much work done on Pakistani number plates because of the unavailability of the data and heterogeneous plate formations. Addressing this issue, we have collected a Pakistani vehicle dataset having various plate configurations and developed a novel ANPR framework using the dataset. The proposed framework localizes the number plate region using the YOLO (You Only Look Once) object detection model, applies robust preprocessing techniques on the extracted plate region, and finally recognizes the plate label using OCR (optical character recognition) Tesseract. The obtained mAP score of the YOLOv3 is 94.3% and the YOLOv4 model is 99.5% on the 0.50 threshold, whereas the average accuracy score of our framework is found to be 73%. For comparison and validation, we implemented a LeNet Convolutional Neural Network (CNN) architecture which uses the segmented image as an input. The comparative analysis shows that the proposed ANPR framework comprising the YOLOv4 and OCR Tesseract has good accuracy and inference time for a wide variation of illumination and style of Pakistani number plates and can be used to develop a real-time system. The proposed ANPR framework will be helpful for researchers developing ANPR for countries having similar challenging vehicle number plate formats and styles.

Highlights

Vehicle ownership is increasing proportionally with the economic growth that makes the management and governance of the transportation system complicated
The last layer comprises a dense layer with 36 outputs and Softmax activation function. e 36 neurons are for the total number of outputs as 26 alphabets and 10 numbers. e learning rate we used for training is 0.001 with 50 epochs, categorical_crossentropy loss function, and Adam optimization function. e Convolutional Neural Network (CNN) model is making predictions with 97.89% accuracy, but after reconstructing the number plate label, the accuracy decreases
YOLO Darknet neural network framework is applied on a single neural network to image, divides the image into the region, and predicts bounding boxes and scoring probabilities for each region. e highest probability is selected as an object detected area

Summary

Introduction

Vehicle ownership is increasing proportionally with the economic growth that makes the management and governance of the transportation system complicated. E detection and retrieval of number plates from fast-moving vehicles make it hard to catch and penalize the culprit. There is a need to have an automatic and efficient device for detecting, collecting, and managing car information. E most important subsystem of an ITS is Automatic Number Plate Recognition (ANPR). E ANPR system reads the image, preprocesses it, and recognizes the vehicle number plate characters independent of human involvement. It helps to identify potential risks, prevent crime, improve reliability, develop barrier-free infrastructure, and provide location information. E Global Automatic Number Plate Recognition System Market is forecasted to increase with a ratio of 9.63% from 2017 to 2025 [1] It helps to identify potential risks, prevent crime, improve reliability, develop barrier-free infrastructure, and provide location information. e Global Automatic Number Plate Recognition System Market is forecasted to increase with a ratio of 9.63% from 2017 to 2025 [1]

Methods

Results

Conclusion