Proceedings of the 2023 Brawijaya International Conference (BIC 2023)

<Previous Article In Volume
Next Article In Volume>

Classification of Rhizomes Using Pre-trained Convolutional Neural Network Method

Authors
Yusuf Hendrawan1, *, Wais Al Qorni1, Gunomo Djoyowasito1, Dimas Firmanda Al Riza1
1Department of Biosystems Engineering, Faculty of Agricultural Technology, Universitas Brawijaya, Jalan Veteran, Malang, 65145, Indonesia
*Corresponding author. Email: yusuf_h@ub.ac.id
Corresponding Author
Yusuf Hendrawan
Available Online 29 October 2024.
DOI
10.2991/978-94-6463-525-6_15How to use a DOI?
Keywords
Convolutional Neural Network; GoogLeNet; Rhizome; ResNet-50
Abstract

Rhizomes have many types, aromas, and colors. Manual identification of rhizome types can be done based on their aroma, shape, and color characteristics. Some types of rhizomes have similarities that are difficult to identify by human vision. The purpose of this study is to identify five types of rhizomes including ginger, A. galanga, curcuma, B. pandurata, and K. galanga appropriately using machine vision methods based on convolutional neural networks (CNN). The samples used in this study were 250 samples of each type of rhizome which were divided into two data sets, namely 200 data for training-validation and 50 data for testing. The pre-trained CNN models used in this study are GoogLeNet and ResNet-50. The results of this study show that GoogLeNet achieved the highest accuracy value of 100% when using the Adam optimizer and a learning rate of 0.00005. Meanwhile, ResNet-50 achieved the highest accuracy of 100% when using the RMSProp optimizer and a learning rate of 0.0001. From the testing results, GoogLeNet and ResNet-50 achieved the highest accuracy of 99.2% and 95.6%, respectively.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 Brawijaya International Conference (BIC 2023)
Series
Advances in Economics, Business and Management Research
Publication Date
29 October 2024
ISBN
978-94-6463-525-6
ISSN
2352-5428
DOI
10.2991/978-94-6463-525-6_15How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Yusuf Hendrawan
AU  - Wais Al Qorni
AU  - Gunomo Djoyowasito
AU  - Dimas Firmanda Al Riza
PY  - 2024
DA  - 2024/10/29
TI  - Classification of Rhizomes Using Pre-trained Convolutional Neural Network Method
BT  - Proceedings of the 2023 Brawijaya International Conference (BIC 2023)
PB  - Atlantis Press
SP  - 133
EP  - 140
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-525-6_15
DO  - 10.2991/978-94-6463-525-6_15
ID  - Hendrawan2024
ER  -