Plant disease detection using deep learning

Abstract

Plant diseases are a serious threat to crop production worldwide, causing economic losses and food insecurity. Early and accurate detection of these diseases is important for appropriate intervention and better product health. In this paper, we present the development of a mobile application for the detection of plant diseases aimed at three major crops: potato, tomato and corn. This application uses a convolutional neural network (CNN) trained on a complete set of images to classify plant leaves into healthy and dead leaves. This model was developed using the Teachable Machine friendly platform and then converted to the TensorFlow Lite model for optimal deployment on Android devices. The Android Studio app allows users to capture images directly or select them from the gallery. The captured images are analyzed by a pre-trained CNN model to provide real-time classification results. If a leaf dies, the application will display the name of the disease and specific symptoms, recommended fertilizers for treatment and possible treatment methods. This study demonstrates the potential of using CNN approaches for plant disease detection in mobile application settings. This application has the potential to empower farmers and agricultural officers with easy-to-use tools to identify early diseases, allowing them to act in time to improve crop health and yields.

Plant phenotyping relevance

植物葉画像から健全・枯死および病害を分類するCNNとモバイルアプリの開発が研究の中心であり、植物の病徴状態を直接推定するフェノタイピング手法に該当する。

Code and data availability

The paper describes a CNN-based plant disease detection app trained on images compiled from three publicly available Kaggle datasets, but no specific Kaggle dataset names, URLs, or identifiers are provided, and no author code, model checkpoints, or data deposits are mentioned. The only allowed URL is the article DOI, a

No evidence-backed public reproduction asset is currently recorded.