Deep learning-based citrus plant disease classification using a computationally efficient CNN model.

Abstract

Recent advancements in domain-specific classification methods have demonstrated the remarkable performance of deep learning in comparison to traditional machine learning techniques. This study develops a computationally efficient Convolutional Neural Network (CNN) model tailored for citrus plant disease classification, achieving performance comparable to that of the pretrained InceptionV3 model. A custom five-layer CNN model is constructed to classify citrus plant diseases into healthy and diseased categories using images collected from citrus orchards in Northen India. The model has been further validated using images sourced from GitHub and the Kaggle database. The proposed method surpasses classical machine learning approaches in accuracy and computational efficiency, achieving classification accuracies of 92.59%. The training time of the proposed CNN AgriVision-L5 is reduced by 50%, respectively, compared to the InceptionV3 model, demonstrating their computational efficiency. The proposed methodology offers significant advancements in plant disease management and sustainable agriculture, aligning with Sustainable Development Goals like SDG2, SDG9, and SDG12.

Plant phenotyping relevance

柑橘病害を画像から分類するCNNを開発し、外部画像で検証しており、植物の病害状態を推定する方法が研究の中心です。

Code and data availability

The paper's primary self-collected citrus disease image dataset (~180 field images from Abohar, Punjab) has no public deposit; the Data availability section only points to third-party GitHub/Kaggle citrus datasets used as an external test set. Those external dataset URLs appear in the text but are mangled with zero-​-​

No evidence-backed public reproduction asset is currently recorded.