0704-883-0675     |      dataprojectng@gmail.com

DEVELOPMENT OF A DEEP LEARNING BASED VEHICLE LICENSE PLATE DETECTION SCHEME

  • Project Research
  • 1-5 Chapters
  • Abstract : Available
  • Table of Content: Available
  • Reference Style: APA
  • Recommended for : Student Researchers
  • NGN 5000

ABSTRACT

This research developed a license plate and classification scheme using deep learning architecture which utilized transfer learning using pre-trained Convolutional Neural Network (CNN). The developed scheme used images obtained from Caltech dataset, Peking University VehicleID (PKU VehicleID) dataset and a developed dataset of vehicle licence plates from Ahmadu Bello University, Zaria called the ABU dataset. De-noising, downscaling operation and grayscale conversion was applied on the acquired image to reduce the cost inqured in using the original image. Sobel operation was performed to detect the edge of the pre-processed image. Edge density filtering and connected component analysis were used to extract and verify the region which constituted the licence plate number. AlexNet model pre-trained on ImageNet was used to extract features and classify the detected license plate candidate’s regions. The performance of the developed scheme was evaluated on 150 images of each dataset of PKU VehicleID, Caltech, and ABU test images taken under different conditions. With the Caltech dataset the scheme achieved a precision rate of 85.10%, recall rate of 98.50%, and recognition accuracy of 98.08% while the PKU VehicleID dataset gave precision rate of 97.91%, recall rate of 97.91%, and accuracy of 100%. For the ABU dataset, the method obtained a precision rate of 95.8%, recall rate of 100%, recognition accuracy of 99.82%. The results for the developed deep learning-based scheme showed some performance improvements of 3.96% and 14.75% in the precision and recall rate, respectively, and 8.15% improvement in recognition rate, when compared with the existing scheme which utilized the edged based approach with SVM and achieved detection rate of 98% on the PKU VehicleID dataset, 90% on the Caltech dataset, and 96% on the ABU dataset in the presence of complex backgrounds and highly variable license plate patterns.




FIND OTHER RELATED TOPICS


Related Project Materials

The effect of online security certifications on customer confidence in banking: a case study of Citibank Nigeria

Background of the Study
Online security certifications serve as a critical assurance mechanism in the digital banking ecos...

Read more
An Examination of the Shift from Brick-and-Mortar Banking to Virtual Banking: A Case Study of Zenith Bank, Abuja

Background of the Study:

The banking industry is witnessing a significant paradigm shift from traditional brick-and-mortar branches to vi...

Read more
An Evaluation of Nurses’ Compliance with Pain Management Protocols for Elderly Patients in Tertiary Hospitals in Gombe State

Background of the Study

Pain management is a critical component of elderly care, particularly for patients suffering from chronic illness...

Read more
EVALUATING GENDER STEREOTYPES IN TECHNICAL CAREER PATHS

ABSTRACT: Addressing Gender Stereotypes in Technical Career Paths is essential for fostering an inclusive and diverse workforce. This study ex...

Read more
EVALUATION ON THE IMPACT OF AGGREGATE SIZES ON CONCRETE STRENGTH

INTRODUCTION

It is common knowledge that coarse aggregate is crucial to the success of concrete. According to studies, c...

Read more
The Effect of Poor Drainage Systems on Vector-Borne Diseases in Kano State

Background of the Study

Vector-borne diseases, such as malaria and dengue fever, remain significant public health threat...

Read more
An appraisal of technological readiness in Islamic financial institutions

Background of the Study

Technological readiness is a critical factor in determining the success of digital transformation in Islamic fina...

Read more
FINANCIAL ACCOUNTING THEORY AND PRACTICES AND CORPORATE GOVERNANCE IN NIGERIA

Abstract

The project examines the link between financial accounting and corporate governance in Nigeria...

Read more
Effectiveness of Managerial Accounting Techniques in Improving Revenue Collection in Niger State

Background of the Study

Revenue collection is a critical function of government and pu...

Read more
An evaluation of customer acquisition strategies in corporate banking: A case study of Fidelity Bank Nigeria, Kano

Background of the Study
Customer acquisition is critical to the success of corporate banking, as it directly influences mar...

Read more
Share this page with your friends




whatsapp