Plant Leaf Disease Classification Using Convolutional Neural Network Based on Digital Images

Abstract

Monitoring plant health is an important factor in maintaining agricultural productivity. Manual identification of leaf diseases requires expert knowledge and is prone to errors due to visual similarities among disease symptoms. This study aims to develop a plant leaf disease classification system based on digital images using a Convolutional Neural Network (CNN) approach. The dataset consists of plant leaf images representing three disease classes: Corn–Common rust, Potato–Early blight, and Tomato–Bacterial spot. Prior to model training, the images undergo preprocessing steps including image resizing and pixel normalization. The performance of the CNN model is evaluated using a testing dataset that is not involved in the training process, employing accuracy, confusion matrix, precision, recall, and F1-score as evaluation metrics. Experimental results show that the proposed model achieves a test accuracy of 95.56%, with balanced performance across all disease classes. In addition to quantitative evaluation, the trained model is implemented in a Streamlit-based application, allowing users to upload plant leaf images and obtain disease classification results interactively. The findings indicate that the CNN-based approach is effective for plant leaf disease classification and has potential application as an early decision-support system for plant health monitoring.

Plant phenotyping relevance

植物葉の画像から病害状態を推定するCNN分類法を開発し、独立テストデータで性能評価しているため、植物フェノタイピング手法が中心である。

Code and data availability

The paper's phenotyping input is a publicly available PlantVillage image dataset (900 leaf images across three disease classes) obtained from Kaggle, with an explicit authors' URL. No author analysis code or trained model is publicly deposited.