基于卷积神经网络和迁移学习的水稻害虫识别  

Rice Pest Identification Based on Convolutional Neural Network and Transfer Learning

作　　者：杨红云[1] 肖小梅 黄琼 郑国梁 易文龙[1] Yang Hongyun;Xiao Xiaomei;Huang Qiong;Zheng Guoliang;Yi Wenlong(School of Software,Jiangxi Agricultural University,Nanchang 330045,Jiangxi,China;School of Computer and Information Engineering,Jiangxi Agricultural University,Nanchang 330045,Jiangxi,China)

机构地区：[1]江西农业大学软件学院,江西南昌330045 [2]江西农业大学计算机与信息工程学院,江西南昌330045

出　　处：《激光与光电子学进展》2022年第16期323-330,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62162030,61562039,61762048)。

摘　　要：为了实现水稻害虫的快速、准确识别,提出了一种基于迁移学习和卷积神经网络相结合的水稻害虫识别方法。首先对水稻害虫图像进行平移、翻转、旋转、缩放等预处理,并按照害虫特征由人工分为稻纵卷叶螟、稻飞虱、二化螟、三化螟、稻蝗、稻象甲等6个类别。然后基于迁移学习方法,将VGG16模型在图像数据集ImageNet上训练得到的权重参数迁移到水稻害虫的识别当中,将VGG16的卷积层和池化层作为特征提取层,同时将顶层重新设计为全局平均池化层和一个softmax输出层,训练时冻结部分卷积层。实验结果表明:所提模型的平均测试准确率为99.05%,训练时间约为原有模型的1/2,模型大小仅为74.2 MB;在稻蝗、稻飞虱、稻象甲、二化螟、稻纵卷叶螟、三化螟等6类害虫的F1值分别为0.98、0.99、0.99、0.99、1.00、0.99。所提方法识别效率高,识别效果好,可移植性强,可为农作物的害虫高效快速诊断提供参考。In order to realize rapid and accurate identification of rice pests,a rice pest identification method based on transfer learning and convolutional neural network was proposed in this paper.First,the images of rice pests were preprocessed.Preprocessing methods include translation,inversion,rotation,and scaling.According to the characteristics of the pests,the images were divided into six categories,namely,rice leaf roller,rice planthopper,rice plant thopper,rice leaf roller,rice plant thopper,rice plant thopper,rice locust,and rice weevil.Then,based on the transfer learning method,the weight parameters trained by the VGG16 model on the image data set ImageNet were transferred to the recognition of rice pests.The convolution layer and the pooling layer of VGG16 were used as the feature extraction layer.Meanwhile,the top layer was redesigned as the global average pooling layer and a softmax output layer.Part of the convolutional layer is frozen during training.The experimental results show that the average test accuracy of this model is 99.05%,the training time is about1/2 of the original model,and the model size is only 74.2 MB.The F1 values of six insect pests,namely,rice grasshopper,rice planthopper,rice weevil,striped rice borer,the rice leaf roller,and yellow rice borer,were 0.898,0.99,0.99,0.99,1.00,0.99,respectively.The experimental results show that this method has high identification efficiency,good identification effect and strong portability,which can provide a reference for the efficient and rapid diagnosis of crop pests.

关 键 词：机器视觉 水稻害虫 迁移学习 VGG16 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S431.9[自动化与计算机技术—计算机科学与技术]