A Convolutional Neural Network (CNN) Based Classification Framework for Multi-Crop Disease Detection using Leaf Images

Abstract

Early and precise diagnosis of crop diseases is crucial for global food security, particularly in developing countries where agriculture still plays a dominant role. This study presents a deep learning approach for labelling ten different plant disease conditions across three principal crops—maize, potato, and soybean. The Convolutional Neural Network (CNN) model incorporates multiple convolutional and batch normalization layers, achieving an overall classification accuracy of 95 %. Class-wise F1-scores range from 0.84 to 0.96, with notably strong performance for the Potato-Healthy and Soybean-Healthy categories. The model demonstrates robust generalization to variations in background, lighting, and leaf orientation, highlighting its suitability for real-world agricultural environments. This work supports the development of automated, scalable, and accurate multi-crop disease detection systems. The study also examines challenges such as class imbalance and overfitting, and proposes improvements including the integration of attention mechanisms and transfer learning. However, the model’s performance is still limited by the relatively small dataset size and restricted environmental diversity, suggesting future scope for expansion through larger field-based datasets, multimodal sensing, and advanced hybrid architectures.

Plant phenotyping relevance

葉画像から植物病害状態を分類するCNN手法が研究の中心であり、精度やF1スコアによる性能評価も行っているため、植物フェノタイピング手法として収録する。

Code and data availability

The paper describes a custom CNN trained on a 1000-image leaf dataset collected from online repositories, but provides no public dataset URL, no code/model deposit, and its Data Availability Statement only claims data are included in the manuscript. No paper-specific public asset is actionable.

No evidence-backed public reproduction asset is currently recorded.