IMAGE CLASSIFICATION OF DISEASES IN WHEAT CROP

Abstract

Wheat is one of the most widely cultivated and essential staple crops, playing a crucialrole in global food security. However, wheat production is significantly affected by various diseasessuch as Yellow Rust, Brown Rust, and Septoria, which lead to reduced yield and economic lossesfor farmers. Early and accurate detection of these diseases remains a major challenge due to relianceon manual inspection and limited access to agricultural expertise [1], [2]. This paper presents animage-based disease classification system for wheat crops using deep learning techniques. Theproposed system utilizes Convolutional Neural Networks (CNNs) to automatically analyze wheatleaf images and classify them into healthy or diseased categories. The model is trained on a labeleddataset of wheat leaf images and is capable of identifying multiple disease types with high accuracy.The system enables efficient and rapid disease detection, reducing dependency on manual methodsand supporting timely decision-making for crop management. Additionally, the integration ofcomputer vision and artificial intelligence improves scalability and can be extended to real-time andmobile-based applications. By leveraging modern deep learning approaches, the proposed solutioncontributes to precision agriculture, enhances productivity, and helps reduce economic losses in thefarming sector

Plant phenotyping relevance

小麦葉画像から健全・罹病状態および病害種を分類する画像ベース手法が研究の中心であり、植物病害状態の表現型推定に該当する。

Code and data availability

The article describes a CNN-based wheat disease classification system but provides no public dataset, image collection, code repository, model checkpoint, or supplement with availability language. Dataset provenance is vague ('wheat leaf images from datasets'), and no authors' public URL or deposit is given. No paper-­

No evidence-backed public reproduction asset is currently recorded.