Pendeteksian Anomali Pada Daun Tanaman Jambu Biji Menggunakan Isodata Cluster
Keywords:
Guava Leaf, Image processing, Clustering, ISODATA, Disease IdentificationAbstract
The purpose of this study is to develop a disease identification system for guava leaves using the ISODATA Clustering method. Diseases affecting guava plants may reduce plant quality and productivity; therefore, an automatic identification system is required. The ISODATA method was selected because it can automatically organize image data through cluster creation, merging, and splitting processes. The system was developed using Visual Studio and utilized guava leaf images as input data. The research stages included image acquisition, pixel extraction, clustering using ISODATA, and disease identification based on color pattern grouping. The results indicate that the ISODATA Clustering method is capable of grouping leaf color patterns and supporting the identification of guava leaf diseases. The developed system classifies leaves into several categories, including leaf blight, leaf spot, rust disease, and healthy leaves. This system is expected to assist farmers in early disease detection and decision-making for prevention and treatment.
Downloads
References
S. Sharma, R. Kumar, and P. Singh, “Guava Leaf Disease Detection Using Support Vector Machine,” Smart Agricultural Technology, vol. 9, pp. 1–12, 2025.
A. Pratama, R. Nugroho, and D. Kurniawan, “Guava Disease Detection and Classification: A Systematic Literature Review,” Jurnal Telematika, vol. 18, no. 2, pp. 112–126, 2025.
M. Rahman, A. Islam, and S. Hossain, “AI-Driven Disease Detection in Guava Plants Using Teachable Machine Learning Models,” Plant Science Today, vol. 13, no. 1, pp. 55–67, 2026.
D. Putra, Pengolahan Citra Digital. Yogyakarta: Andi Publisher, 2010.
D. Putra, Pengolahan Citra Digital dan Aplikasinya. Yogyakarta: Andi Publisher, 2017.
A. Saputra, B. Nugraha, and M. Rizky, “Plant Disease Detection Using Image Processing and Machine Learning,” International Journal of Artificial Intelligence and Machine Learning, vol. 4, no. 1, pp. 22–31, 2026.
R. Gupta and P. Sharma, “Image Segmentation Techniques for Plant Disease Detection: A Comprehensive Review,” Journal of Precision Agriculture Systems, vol. 7, no. 2, pp. 88–105, 2026.
H. Halim and F. Syahputra, “Segmentation Analysis for Digital Image Processing Applications,” Journal of Computer Vision Research, vol. 5, no. 1, pp. 10–18, 2024.
Y. Chen, J. Li, and X. Wang, “Plant Disease Segmentation Networks for Fast Automatic Detection,” Agriculture, vol. 15, no. 6, pp. 1–19, 2025.
Y. Lu and K. Huang, “ISODATA Clustering Algorithm for Image Segmentation Applications,” International Journal of Image Processing, vol. 8, no. 4, pp. 201–210, 2024.
N. Memarsadeghi, D. Mount, N. Netanyahu, J. LeMoigne, and R. Chellappa, “A Fast Implementation of the ISODATA Clustering Algorithm,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 5, pp. 1–12, 2007.
L. G. Shapiro and G. C. Stockman, Computer Vision. New Jersey, NJ, USA: Prentice Hall, 2000.
F. Ramadhan, M. Akbar, and D. Prasetyo, “CNN-Based Deep Learning Utilization Model for Crystal Guava Disease Detection,” Journal of Applied Smart Systems and Intelligent Machine Engineering, vol. 5, no. 1, pp. 15–26, 2026.
P. Kumar, R. Singh, and S. Verma, “Hybrid CNN-ViT Framework for Guava Leaves and Fruits Disease Classification,” in Proc. International Conference on Artificial Intelligence and Information Technology, 2026, pp. 44–50.
A. Fernandez, M. Torres, and L. Gomez, “Enhancing Image-Based Classification for Crop Disease Detection Using Deep Learning,” Scientific Reports, vol. 15, pp. 1–14, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nadila Harianti, Yunita Sari, Mufida Khairani
This work is licensed under a Creative Commons Attribution 4.0 International License.
Universitas Harapan Medan
.png)
.png)
.png)
.png)
.png)
