Potato Crop Disease Detection Using Deep Learning

Abstract

This paper presents the design and implementation of a Potato Crop Disease Detection system utilizing deep learning for accurate classification and early diagnosis. The system employs convolutional neural networks to analyze images of potato plants, identifying various diseases such as late blight, early blight, and bacterial wilt. By leveraging advanced image processing techniques and a large dataset of annotated potato plant images, the model achieves high accuracy in distinguishing between healthy and diseased specimens. This automated approach offers farmers a rapid and reliable tool for monitoring crop health, enabling timely interventions to prevent yield losses and reduce the need for extensive pesticide use. The system integrates a convolutional neural network (CNN) model trained on a dataset of diseased and healthy potato leaf images to identify infections with high precision. A camera module captures real-time images, which are processed to detect symptoms such as blight, mosaic virus, and leaf spot. Additionally, a mobile application provides instant feedback, enabling farmers to take timely preventive measures. The combination of image processing, machine learning, and real-time monitoring enhances the efficiency and reliability of disease detection, making it a valuable tool for sustainable agriculture.

Plant phenotyping relevance

ジャガイモ葉の画像から病徴・病害状態を推定する画像ベース手法とCNNシステムが研究の中心であり、植物表現型計測に該当する。

Code and data availability

The paper describes a CNN/EfficientNet potato disease detection system but provides no dataset link, code repository, model checkpoint, or data availability statement. No public, paper-specific assets are identified, and no allowed URLs are available.

No evidence-backed public reproduction asset is currently recorded.