A CNN CLASSİFİCATİON APPROACH FOR POTATO PLANT LEAF DİSEASE DETECTİON

Abstract

The timely detection and management of plant diseases is critical in the agricultural industry. Among these, potato leaf diseases can have a major impact on crop productivity and quality. This research addresses the important requirement for rapid and reliable disease detection in potato plants. Using Convolutional Neural Networks (CNNs), a sophisticated deep learning approach, we gain considerable progress in automating the identification process. We demonstrate the models ability to distinguish diverse kinds of disease with an amazing accuracy rate of 98.8% through rigorous experimentation. The use of data augmentation techniques improves the models flexibility to a variety of environmental situations. This breakthrough has significant promise for shaping agricultural methods, providing a powerful tool for early disease intervention, and ensuring global food security. KEYWORDS - Deep learning, Convolutional Neural Network (CNN), potato diseases, TensorFlow, Streamlit.

Plant phenotyping relevance

CNNによるジャガイモ葉の病徴・病害状態の画像分類手法を開発・評価しており、植物フェノタイピング手法が中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.