Abstract

This paper explores the use of Convolutional Neural Networks in classifying images of date fruits as one of 9 varieties, creating several models with the highest achieving 97% accuracy. It contributes an original dataset of 1658 high-quality images taken in a controlled environment for use in both the computer vision and agricultural technology fields. A range of models is explored and trained, both with and without data augmentation, leading to high classification accuracy.

Publication Type:	Article
Additional Information:	This is a pre-print of an article to be published in Advances in Intelligent Systems and Computing. The final authenticated version will be available online at: http://www.springer.com/series/11156?detailsPage=titles
Publisher Keywords:	Convolutional Neural Networks, supervised learning, classification, date fruit
Subjects:	Q Science > QK Botany R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Departments:	School of Mathematics, Computer Science & Engineering > Computer Science
Date Deposited:	28 Oct 2020 11:37
URI:	https://openaccess.city.ac.uk/id/eprint/25158

Text - Accepted Version This document is not freely accessible due to copyright restrictions. To request a copy, please use the button below. Request a copy

Export

Downloads