A TensorFlow-Based CNN Model for Widespread Detection of Rice and Potato Leaf Diseases

Abstract

Abstract Rice and potatoes are major crops in Bangladesh, frequently affected by major disease outbreaks that challenge food security. Inaccurate disease identification often contributes to yield losses. Recently, machine learning garnered much attention in identifying crop diseases. The present study was conducted to develop a deep learning model-based image‑analysis system that automatically identifies key diseases of Bangladeshi rice and potato, and integrates it into a web app to provide farmers with rapid, accurate diagnoses. The system employs a convolutional neural network (CNN) implemented with TensorFlow’s Sequential API, featuring ReLU-activated hidden layers and a Softmax output layer. A dataset of 4,809 images, comprising both healthy and diseased, was collected and processed through pre-processing, feature extraction, and classification. A web-based application was deployed utilizing the Python Streamlit framework. This application integrates the proposed model to predict 2 rice diseases viz. blast ( Magnaporthe oryzae ), bacterial leaf blight ( Xanthomonas campestris ), and 2 potato diseases viz. Early blight (Alternaria solani) and Late blight ( Phytophthora infestans ) from uploaded images, providing a confidence score for the predictions with approximately 92.84% for all detected diseases. The proposed model achieved a training accuracy of 0.9357, a validation accuracy of 0.8983, and a test accuracy of 0.9333. The developed web application indicates strong diagnostic performance for four major diseases, offering Bangladeshi farmers an accessible tool to make timely management decisions.

Plant phenotyping relevance

イネ・ジャガイモ葉の病徴を画像から分類するCNNと実用Webアプリを開発・評価しており、植物の病害状態推定が中心的な方法論的貢献である。

Code and data availability

The paper's rice/potato leaf disease image dataset partially comes from Kaggle, and the data availability statement points to PlantVillage for additional image data; both are public image assets used for the paper's CNN phenotyping/disease-classification analysis. No author analysis code, trained model checkpoints, or专