Reliability Testing of Single Channel Co-Occurrence Matrix Texture Feature Extraction for Avocado Leaf Classification

DOI

10.2991/978-94-6463-445-7_7How to use a DOI?

Keywords

Avocado leaf disease; GLCM feature extraction; majority voting accuracy

Abstract

There are quite a lot of superior types of avocado that are known to the public today. However, it isn't easy to differentiate one type from another based on the leaves. These can cause errors in variety selection, which can cause losses. Machine learning methods can help recognize avocado types based on leaves. This research uses the GLCM (Gray Level Co-occurrence Matrix) method which is applied to single-channel in the YUV color space, not GLCM in general. These have been proven effective in several previous studies. To measure the reliability of this feature extraction method, this study used four cameras of different brands and resolutions. The feature extraction results are then classified using several classification methods: SVM (Support Vector Machine), KNN (K-Nearest Neighbor), and Random Forest. To further increase accuracy, majority voting was carried out for the three classifiers. By conducting majority voting, it has proven successful in increasing accuracy compared to a single classifier. The highest classification results were achieved by the Random Forest classifier with an accuracy of 85.83%, and the results successfully increased to 87.50% by applying majority voting. This indicates that the selected feature extraction method is relatively reliable even when mixing datasets from camera sources with different specifications.

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)

TY  - CONF
AU  - Dwiretno Istiyadi Swasono
AU  - Achmad Maududie
AU  - Niki Putri Hadi Pradani
PY  - 2024
DA  - 2024/06/29
TI  - Reliability Testing of Single Channel Co-Occurrence Matrix Texture Feature Extraction for Avocado Leaf Classification
BT  - Proceedings of the 2nd International Conference on Neural Networks and Machine Learning 2023 (ICNNML 2023)
PB  - Atlantis Press
SP  - 55
EP  - 61
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-445-7_7
DO  - 10.2991/978-94-6463-445-7_7
ID  - Swasono2024
ER  -