Open AccessPerformance Evaluation for Vision-Based Vehicle Classification Using Convolutional Neural Network
Author(s) -
Raja Durratun Safiyah,
Zaid Abdul Rahim,
Syamsul Syafiq,
Zarina Bibi İbrahim,
Nurbaity Sabri
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.15.17507
Subject(s) - convolutional neural network , computer science , artificial intelligence , task (project management) , pattern recognition (psychology) , computer vision , artificial neural network , deep learning , contextual image classification , image (mathematics) , machine learning , engineering , systems engineering
Vision-based vehicle classification is a very challenging task due to vehicle pose and angle variations, weather conditions, lighting quality, and limited number of available datasets for training. It can be applied for driver assistance system and autonomous vehicles. This paper conducted a performance evaluation for this task based on three Convolutional Neural Network (CNN) models, which are simple CNN, and pre-trained CNN models that are AlexNet and GoogleNet. A dataset of more than 7000 images from the Image Processing Group (IPG) has been used for training and testing and the results indicate that AlexNet achieves the best classification result that is 65.09%. This result is obtained because of the variations of the quality of the images.