Performance Evaluation of Plant Leaf Disease Detection using Structural Modification of the Traditional Convolutional Neural Networks

Abstract

Plant diseases reduce agricultural productivity, and farmers struggle to precisely identify and control these diseases which leads to crop losses. The early identification of plant diseases is a challenging task in agriculture due to the variation in the size, shape, colour, and texture caused by environmental changes. This research employs convolutional neural networks (CNNs) for the identification of plant leaf diseases, namely, corn common rust, potato early blight, and tomato bacterial spot. The model was trained with the augmented dataset on 15 epochs with and without the additional convolution layer in the CNN architecture. The accuracy achieved by CNN without adding additional layers is 99.4% and after adding additional layers, the accuracy is 75.5% at 10 epoch. These results show that the proposed method can be optimized in the future and can be used as the most effective method in predicting plant leaf disease. This model may lead to enhanced crop yields and quality by rapid prediction of leaf diseases.

Plant phenotyping relevance

植物葉の病害状態を画像から推定するCNN手法が研究の中心であり、構造変更と性能比較による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採用する。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.