The study of deep learning for automotive logo recognition and classification

Authors

  • Saeed R. Saeed, et. al.

DOI:

https://doi.org/10.21533/pen.v11.i3.151

Abstract

Most vehicle manufacturer recognition (VMR) techniques are established in vehicle logo recog-nition because a vehicle's logo is the most obvious sign from the vehicle's manufacturer. Howev-er, due to the difficulty in accurately segmenting a vehicle logo on the picture with demand in resilience against many imaging scenarios, logo recognition can still be challenging. After sub-jective overview about this scope, a convolutional neural network (CNN) method for VMR is investigated in this research, which does away with the need for exact logo detection and seg-mentation. A powerful pertaining approach has also been developed to improve real-world appli-cations to lower the high computational cost for kernel training on CNN-based systems. The con-tribution of this paper is to study the multiclass logo employing random forest ensemble learn-ing and convolution mapping in nonlinear space. To boost accuracy by roughly 35%, 800 images from 15 types of car classes were investigated in the paper.

Downloads

Published

2023-05-03

Issue

Section

Articles

How to Cite

Saeed, et. al., S. R. (2023). The study of deep learning for automotive logo recognition and classification. Periodicals of Engineering and Natural Sciences, 11(3), 255-268. https://doi.org/10.21533/pen.v11.i3.151