基于预训练CNN模型深度特征融合的苹果叶片病害检测
Detection of Enhanced Apple Leaf Disease Using Fused Deep Features from Pre-trained CNNs
张正风 1高峰1
作者信息
- 1. 徐州生物工程职业技术学院,江苏徐州 221006
- 折叠
摘要
探讨了采用预训练的卷积神经网络(CNN)模型,如GoogLeNet、VGGNet和EfficientNet,作为特征提取器对苹果叶片病害检测准确率的影响.通过结合这3个CNN模型导出的深度特征,实现了深度学习特征的组合,使用提取的深度特征训练了支持向量机(SVM)分类器.结果表明,所有CNN模型都能以显著的准确率使用深度特征提取并检测出苹果叶片病害,整体分类准确率达到了 99.42%.此外,该研究还提出了一种基于改进深度学习的方法,通过结合3 个CNN模型的深度特征,进一步提高了预测性能.该方法在苹果叶片病害检测中表现出色,并有望应用于其他植物叶片的病害检测.该研究为植物病害的自动识别提供了一种有效的方法,有助于农业生产的智能化和精准化.
Abstract
A comprehensive examination of the application of pre-trained Convolutional Neural Networks(CNNs)was discussed,such as GoogLeNet,VGGNet and EfficientNet in detecting apple leaf diseases and pests.By addressing the limitations and gaps in existing research,we focused on enhancing detection accuracy by leveraging deep features extracted from these CNN models.The methodology involved the fu-sion of deep features obtained from the final fully connected layers of the CNNs,followed by the training of a Support Vector Machine(SVM)classifier.Results showed that all the CNN models demonstrated significant accuracy in detecting apple leaf diseases using deep feature extrac-tion,achieving an overall classification accuracy of 99.42%.Furthermore,an improved deep learning approach was introduced which com-bined the deep features from the three CNN models,further boosting predictive performance.The methodology exhibited promising results in apple leaf disease detection and had potential applications in detecting diseases in other plant leaves.This research contributed to the develop-ment of automated and precise plant disease identification techniques,paving the way for intelligent and targeted agricultural production.
关键词
苹果叶片病害/卷积神经网络/深度特征提取/支持向量机/病害检测Key words
Apple leaf diseases/Convolutional Neural Networks(CNNs)/Deep feature extraction/Support Vector Machine(SVM)/Disease detection引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据