Classification of brand images using convolutional neural networks
Loading...
Author (Corporation)
Publication date
2023
Typ of student thesis
Course of study
Collections
Type
04B - Conference paper
Editor (Corporation)
Supervisor
Parent work
Proceedings of the 14th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2022)
Special issue
DOI of the original publication
Series
Lecture Notes in Networks and Systems
Series number
648
Volume
Issue / Number
Pages / Duration
528–539
Patent number
Publisher / Publishing institution
Springer
Place of publication / Event location
Cham
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
This paper investigates the classification of brand images using convolutional neural networks. Traditionally, the images must be manually named, classified, and tagged, which is a laborious and time-consuming task. Nowadays, these processes can be addressed with the help of computer vision for brand classification. An approach to create a Convolutional Neural Network (CNN) model with a high accuracy is proposed and discussed, in which the images in the classification process are automatically tagged with the predicted class name.
Keywords
Subject (DDC)
Event
14th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2022)
Exhibition start date
Exhibition end date
Conference start date
14.12.2022
Conference end date
16.12.2022
Date of the last check
ISBN
978-3-031-27523-4
978-3-031-27524-1
978-3-031-27524-1
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Closed
License
Citation
Ruf, Y., Hanne, T., & Dornberger, R. (2023). Classification of brand images using convolutional neural networks. In A. Abraham, T. Hanne, N. Gandhi, P. M. Mishra, A. Bajaj, & P. Siarry (Eds.), Proceedings of the 14th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2022) (pp. 528–539). Springer. https://doi.org/10.1007/978-3-031-27524-1_50