Yuan Yongqi, Sun Jinhua, Zhang Qian
School of Information Technology, Jiangsu Open University, Nanjing 210000, China.
School of Design, Jiangsu Open University, Nanjing 210000, China.
J Imaging. 2024 Nov 2;10(11):279. doi: 10.3390/jimaging10110279.
Traditional machine learning methods struggle with plant pest and disease image recognition, particularly when dealing with small sample sizes, indistinct features, and numerous categories. This paper proposes an improved ResNet34 model (ESA-ResNet34) for crop pest and disease detection. The model employs ResNet34 as its backbone and introduces an efficient spatial attention mechanism (effective spatial attention, ESA) to focus on key regions of the images. By replacing the standard convolutions in ResNet34 with depthwise separable convolutions, the model reduces its parameter count by 85.37% and its computational load by 84.51%. Additionally, Dropout is used to mitigate overfitting, and data augmentation techniques such as center cropping and horizontal flipping are employed to enhance the model's robustness. The experimental results show that the improved algorithm achieves an accuracy, precision, and F1 score of 87.09%, 87.14%, and 86.91%, respectively, outperforming several benchmark models (including AlexNet, VGG16, MobileNet, DenseNet, and various ResNet variants). These findings demonstrate that the proposed ESA-ResNet34 model significantly enhances crop pest and disease detection.
传统的机器学习方法在植物病虫害图像识别方面存在困难，尤其是在处理小样本量、特征不明显和类别众多的情况时。本文提出了一种用于作物病虫害检测的改进型ResNet34模型（ESA-ResNet34）。该模型以ResNet34作为骨干网络，并引入了一种高效的空间注意力机制（有效空间注意力，ESA）来聚焦图像的关键区域。通过将ResNet34中的标准卷积替换为深度可分离卷积，该模型的参数数量减少了85.37%，计算量减少了84.51%。此外，使用随机失活（Dropout）来减轻过拟合，并采用诸如中心裁剪和水平翻转等数据增强技术来提高模型的鲁棒性。实验结果表明，改进后的算法分别实现了87.09%、87.14%和86.91%的准确率、精确率和F1分数，优于几个基准模型（包括AlexNet、VGG16、MobileNet、DenseNet和各种ResNet变体）。这些发现表明，所提出的ESA-ResNet34模型显著增强了作物病虫害检测能力。
