Title: Car Brand Classification Using Deep Learning with ResNet50
Authors: Mohammed I. M. Al-Laham, Samy S. Abu-Naser
Volume: 10
Issue: 2
Pages: 42-49
Publication Date: 2026/02/28
Abstract:
Car brand recognition is considered one of the most challenging problems in computer vision due to the large number of vehicle models, variations in lighting conditions, viewpoints, and background complexity. With the rapid development of deep learning techniques, convolutional neural networks (CNNs) have become the most effective approach for image classification tasks. In this paper, we propose a deep learning-based system for automatic car brand classification using the ResNet50 architecture and a custom dataset containing images of 50 different car brands. The proposed model is trained on a dataset consisting of more than 3000 vehicle images collected from various online sources. The dataset is divided into training and validation sets using an appropriate split ratio. Transfer learning is employed by fine-tuning a pre-trained ResNet50 model on the ImageNet dataset. Experimental results demonstrate that the proposed approach achieves high classification accuracy and shows strong generalization performance across different car brands. The obtained results confirm that deep learning models, particularly ResNet-based architectures, are highly suitable for car brand recognition applications and can be effectively used in intelligent transportation systems, surveillance, and smart city solutions.