Rice Leaf Disease Classification Using Convolutional Neural Network EfficientNetB4 with Gaussian Filter

Abstract

Rice (Oryza sativa) is a vital global food crop, despite its importance, rice production is often hindered by leaf diseases, such as Leaf Scald and Bacterial Leaf Blight, which can significantly reduce yields. Conventional disease diagnosis techniques are often error-prone and inefficient. To address this, A deep learning-based approach using EfficientNetB4 architecture was proposed and combined with a Gaussian filter for enhanced image preprocessing. The Gaussian filter reduces noise and enhancing image, while EfficientNetB4 leverages its optimized depth, width, and resolution scaling for accurate classification. The dataset consists of 2,627 rice leaf images categorized into six classes and divided into training, validation, and testing. Preprocessing includes resizing images to$224 \times 224$pixels, data augmentation, and Gaussian filtering with$5 \times 5$kernel and standard deviation value is 1. The model is evaluated using$\text{F 1}$-score, precision, recall, and accuracy. Results demonstrate that EfficientNetB4 with Gaussian filtering achieves 97.62 % accuracy, outperforming the unfiltered model 96.19 %. This highlights the efficacy of Gaussian filtering in improving feature extraction and classification performance for rice leaf diseases.

Plant phenotyping relevance

イネ葉の病害状態を画像から分類する深層学習手法が中心であり、画像前処理と分類性能を評価しているため、植物病害フェノタイピング手法として含める。

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.