用深度学习和可解释AI提升南瓜叶病识别准确率
Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures
- 对比多种CNN模型，ResNet50在南瓜叶病数据集上表现最优
- 模型准确率达90.5%，且各指标均衡，具备实用价值
- 结合Grad-CAM等技术，让模型决策过程透明可信
南瓜叶病是影响农业产量的重要威胁，需及时精准诊断以有效管理。传统识别方法耗时且易出错，亟需自动化解决方案。本研究基于包含2000张高分辨率图像的'Pumpkin Leaf Disease Dataset'，涵盖霜霉病、白粉病、花叶病、细菌性斑点病及健康叶片五类。数据来自多个农田，确保训练代表性。我们比较了DenseNet201、DenseNet121、DenseNet169、Xception、ResNet50、ResNet101和InceptionResNetV2等多种深度学习架构，发现ResNet50表现最佳，准确率达90.5%，精度、召回率与F1分数均表现良好。通过Grad-CAM、Grad-CAM++、Score-CAM和Layer-CAM等可解释AI（XAI）方法，揭示模型决策依据，增强对自动化诊断的信任。结果表明，ResNet50有潜力推动南瓜叶病检测革新，实现更早更准的防治。
原文摘要 · Abstract (English)
Pumpkin leaf diseases are significant threats to agricultural productivity, requiring a timely and precise diagnosis for effective management. Traditional identification methods are laborious and susceptible to human error, emphasizing the necessity for automated solutions. This study employs on the "Pumpkin Leaf Disease Dataset", that comprises of 2000 high-resolution images separated into five categories. Downy mildew, powdery mildew, mosaic disease, bacterial leaf spot, and healthy leaves. The dataset was rigorously assembled from several agricultural fields to ensure a strong representation for model training. We explored many proficient deep learning architectures, including DenseNet201, DenseNet121, DenseNet169, Xception, ResNet50, ResNet101 and InceptionResNetV2, and observed that ResNet50 performed most effectively, with an accuracy of 90.5% and comparable precision, recall, and F1-Score. We used Explainable AI (XAI) approaches like Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM to provide meaningful representations of model decision-making processes, which improved understanding and trust in automated disease diagnostics. These findings demonstrate ResNet50's potential to revolutionize pumpkin leaf disease detection, allowing for earlier and more accurate treatments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。