A Lightweight and Explainable DenseNet-121 Framework for Grape Leaf Disease Classification

TL;DR

This paper introduces a lightweight, explainable DenseNet-121-based framework for accurate grape leaf disease classification, emphasizing interpretability, efficiency, and robustness for real-world vineyard management.

Contribution

The study presents an optimized DenseNet-121 model with domain-specific preprocessing and Grad-CAM interpretability, outperforming baseline CNNs in accuracy and computational efficiency for grape disease detection.

Findings

Achieved 99.27% accuracy and 99.28% F1 score.

Model inference time is 9 seconds, suitable for real-time use.

Grad-CAM highlights physiologically relevant disease regions.

Abstract

Grapes are among the most economically and culturally significant fruits on a global scale, and table grapes and wine are produced in significant quantities in Europe and Asia. The production and quality of grapes are significantly impacted by grape diseases such as Bacterial Rot, Downy Mildew, and Powdery Mildew. Consequently, the sustainable management of a vineyard necessitates the early and precise identification of these diseases. Current automated methods, particularly those that are based on the YOLO framework, are often computationally costly and lack interpretability that makes them unsuitable for real-world scenarios. This study proposes grape leaf disease classification using Optimized DenseNet 121. Domain-specific preprocessing and extensive connectivity reveal disease-relevant characteristics, including veins, edges, and lesions. An extensive comparison with baseline CNN models, including ResNet18, VGG16, AlexNet, and SqueezeNet, demonstrates that the proposed model exhibits superior performance. It achieves an accuracy of 99.27%, an F1 score of 99.28%, a specificity of 99.71%, and a Kappa of 98.86%, with an inference time of 9 seconds. The cross-validation findings show a mean accuracy of 99.12%, indicating strength and generalizability across all classes. We also employ Grad-CAM to highlight disease-related regions to guarantee the model is highlighting physiologically relevant aspects and increase transparency and confidence. Model optimization reduces processing requirements for real-time deployment, while transfer learning ensures consistency on smaller and unbalanced samples. An effective architecture, domain-specific preprocessing, and interpretable outputs make the proposed framework scalable, precise, and computationally inexpensive for detecting grape leaf diseases.