| Issue |
E3S Web Conf.
Volume 595, 2024
5th International Conference on Agribusiness and Rural Development (IConARD 2024)
|
|
|---|---|---|
| Article Number | 02004 | |
| Number of page(s) | 9 | |
| Section | Agricultural Technology and Smart Farming | |
| DOI | https://doi.org/10.1051/e3sconf/202459502004 | |
| Published online | 22 November 2024 | |
Comparison of Extracted Haar Wavelet Features for Herbal Leaf Type Classification
1 Department of Electrical Engineering, Center of Artificial Intelligence and Robotics Studies, Faculty of Engineering, Universitas Muhammadiyah Yogyakarta, Indonesia
2 Department of Electrical Engineering, Faculty of Engineering, Universitas Muhammadiyah Yogyakarta, Indonesia
3 Faculty of Electrical Engineering and Technology, Universiti Malaysia Perlis (UniMAP), Arau, Malaysia
* Corresponding author: yjusman@umy.ac.id
Plants are incredibly beneficial to human survival in various ways. Leaves are part of plants widely used as medicine. They are similar in shape but have different advantages. Leaf types can only be identified by experts. This study aims to create a classification system for herbal leaves based on the Haar wavelet transform and machine learning. The study was carried out to assist ordinary people in recognizing herbal leaves. The results revealed that Haar wavelet level 1 was better suited to the leaf data. The Quadratic SVM model yielded the highest result with an accuracy of 77%, a precision of 83%, a recall of 83%, a specificity of 82%, and an F-score of 73%.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.