杨明欣, 张耀光, 刘涛. 基于卷积神经网络的玉米病害小样本识别研究[J]. 中国生态农业学报(中英文), 2020, 28(12): 1924-1931. DOI: 10.13930/j.cnki.cjea.200375
引用本文: 杨明欣, 张耀光, 刘涛. 基于卷积神经网络的玉米病害小样本识别研究[J]. 中国生态农业学报(中英文), 2020, 28(12): 1924-1931. DOI: 10.13930/j.cnki.cjea.200375
YANG Mingxin, ZHANG Yaoguang, LIU Tao. Corn disease recognition based on the Convolutional Neural Network with a small sampling size[J]. Chinese Journal of Eco-Agriculture, 2020, 28(12): 1924-1931. DOI: 10.13930/j.cnki.cjea.200375
Citation: YANG Mingxin, ZHANG Yaoguang, LIU Tao. Corn disease recognition based on the Convolutional Neural Network with a small sampling size[J]. Chinese Journal of Eco-Agriculture, 2020, 28(12): 1924-1931. DOI: 10.13930/j.cnki.cjea.200375

基于卷积神经网络的玉米病害小样本识别研究

Corn disease recognition based on the Convolutional Neural Network with a small sampling size

  • 摘要: 农作物病害治理对于农作物的产量和品质有着非常重要的影响。本文针对玉米病害人工识别困难、识别过程耗费大量的人力成本和病害数据样本小且分布不均的问题,提出了一种改进的迁移学习神经网络(Neural Network)的病害识别方法。首先,采用旋转、翻转等方法对样本图像集进行数据增强;其次,通过迁移的MobileNetV2模型在玉米病害图像数据集上训练,利用Focal Loss函数改进神经网络的损失函数;最后,通过Softmax分类方法实现玉米病害图像识别。另外通过试验对比AlexNet、GooleNet、Vgg16、RestNet34、MobileNetV2和迁移的MobileNetV2这6种模型的训练集准确率、验证集准确率、权重、参数数量和运行时间。结果显示,6种模型验证集的准确率分别为93.88%、95.48%、91.69%、97.67%、96.21%和97.23%,迁移的MobileNetV2的准确率最高,且权重仅有8.69 MB。进一步通过混淆矩阵对比了MobileNetV2和迁移的MobileNetV2两种模型,迁移的MobileNetV2模型识别正确率提升1.02%,训练速度减少6 350 s。本文提出迁移的MobileNetV2模型对玉米病害小样本的识别效果最佳,具备更好的收敛速度与识别能力,同时能够降低模型的运算量并大幅度缩短识别时间。

     

    Abstract: Crop disease management influences yield and quality, yet identifying corn diseases is still difficult. High labor costs, small number of sample, and uneven disease distributions contribute to the difficulty. We propose an improved Convolutional Neural Network (CNN) model based on the transfer learning method for disease identification. The sample image set was enhanced by rotation and roll-over, then the migrated MobileNetV2 model was used to train the image data set for corn diseases. The Focal Loss function was used to improve the neural network loss function, and the Softmax classification method was used for corn disease image recognition. The training set accuracy, validation set accuracy, weight, run time, and the number of parameter in six models were experimentally compared. The verification set accuracy rates were 93.88% (AlexNet), 95.48% (GoogleNet), 91.69% (Vgg16), 97.67% (RestNet34), 96.21% (MobileNetV2), and 97.23% (migrated MobileNetV2). The migrated MobileNetV2 was 97.23% accurate and weighed 8.69 MB. Confounding the MobileNetV2 model improved the recognition accuracy by 1.02% and reduced the training speed by 6 350 seconds compared to the unconfounded model. The migrated MobileNetV2 model had the best corn disease recognition ability with a small sampling size; improved convergence speed, reduced model calculations, and greatly improved the recognition time.

     

/

返回文章
返回