Classification of Leaf Disease in Potato Plants Based on Color and Texture Features Using the K Nearest Neighbor (KNN) Method

Andi Sri Bulan, Ingrid Nurtanio

2025

Abstract

Potato (Solanum tuberosum) is an essential food commodity after rice and wheat, widely cultivated in Indonesia’s highlands due to its high economic value. However, production is frequently threatened by leaf diseases such as early blight (Alternaria Solani), late blight (Phytophthora infestans), leaf spot, mosaic virus (PVY), leaf roll, blackleg, soft rot, fusarium wilt, bacterial wilt, and rhizoctonia canker. These diseases reduce yield and quality, leading to economic losses. This study proposes a potato leaf disease classification system by combining color and texture features with Principal Component Analysis (PCA) for dimensionality reduction and K-Nearest Neighbor (KNN) as the classifier. The dataset consisted of 1,055 leaf images collected from Malino, South Sulawesi, expanded through augmentation to 1,155 images across 12 classes (healthy + 11 diseases). Preprocessing included resizing, color space conversion, and segmentation. The optimized KNN model with PCA (k=1, PCA=14) achieved 97.78% accuracy on test data, outperforming Support Vector Machine (SVM) and Random Forest. These results confirm that simple handcrafted features with lightweight classifiers can achieve competitive performance compared to deep learning approaches, making them suitable for mobile-based agricultural applications in resource-limited environments to support early disease detection.

Paper Citation

in Harvard Style

Bulan A. and Nurtanio I. (2025). Classification of Leaf Disease in Potato Plants Based on Color and Texture Features Using the K Nearest Neighbor (KNN) Method. In Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH; ISBN 978-989-758-784-9, SciTePress, pages 61-67. DOI: 10.5220/0014272800004928

in Bibtex Style

@conference{ritech25,
author={Andi Sri Bulan and Ingrid Nurtanio},
title={Classification of Leaf Disease in Potato Plants Based on Color and Texture Features Using the K Nearest Neighbor (KNN) Method},
booktitle={Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH},
year={2025},
pages={61-67},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0014272800004928},
isbn={978-989-758-784-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH
TI - Classification of Leaf Disease in Potato Plants Based on Color and Texture Features Using the K Nearest Neighbor (KNN) Method
SN - 978-989-758-784-9
AU - Bulan A.
AU - Nurtanio I.
PY - 2025
SP - 61
EP - 67
DO - 10.5220/0014272800004928
PB - SciTePress