Enhancing Vehicle Classification Accuracy: A Convolutional Neural Network (CNN) Based Model

Authors

  • Rashid Iqbal MS Scholar, Department of Computer Science and IT, University of Balochistan, Quetta-Pakistan.
  • Dr. Abdul Basit Assistant Professor, Department of Computer Science and IT, University of Balochistan, Quetta-Pakistan.

DOI:

https://doi.org/10.5281/zenodo.11074270

Keywords:

Vehicle Detection, Transfer Learning, Fine-tuned, CNN, Inception V3, VGG-16

Abstract

Using the convolutional neural network (CNN) fine-tuned method, this article introduces a vehicle categorization system. The system's goal is to properly categorize popular vehicle types in the domestic market, which will help with traffic control, monitoring, and traffic accident prevention. The efficacy of VGG-16 and Inception V3 architectures is demonstrated by their evaluation of a real-world dataset consisting of 2000 photos of vehicles. While VGG-16 attains an accuracy of 99.11%, Inception V3 reaches an accuracy of 96.43%. In terms of overall accuracy, VGG-16 outperforms Inception V3, highlighting the importance of architectural decisions in achieving accurate vehicle classification. The suggested technique significantly improves computer vision applications in the domain of vehicle classification, making valuable contributions to traffic management and accident prevention efforts.

Downloads

Download data is not yet available.

Downloads

Published

2024-06-09

How to Cite

Iqbal, R., & Dr. Abdul Basit. (2024). Enhancing Vehicle Classification Accuracy: A Convolutional Neural Network (CNN) Based Model . LC International Journal of STEM (ISSN: 2708-7123), 5(1), 1-12. https://doi.org/10.5281/zenodo.11074270