基于深度卷积神经网络的柑橘黄龙病症状识别  

Recognition of Huanglongbing symptom based on deep convolutional neural network

作　　者：戴泽翰 郑正[1] 黄莉舒 赖云燕 鲍敏丽 许美容[1] 邓晓玲[1] DAI Zehan;ZHENG Zheng;HUANG Lishu;LAI Yunyan;BAO Minli;XU Meirong;DENG Xiaoling(College of Agriculture,South China Agricultural University,Guangzhou 510642,China)

机构地区：[1]华南农业大学农学院,广东广州510642

出　　处：《华南农业大学学报》2020年第4期111-119,共9页Journal of South China Agricultural University

基　　金：广西科技重大专项“柑橘黄龙病综合防控技术研究与示范”(桂科AA18118027-2)。

摘　　要：【目的】探究深度学习在柑橘Citrus spp.黄龙病症状识别上的可行性,并评估识别器的识别准确率。【方法】以黄龙病/非黄龙病引起的发病叶片图像及健康叶片图像为训练素材,基于卷积神经网络及迁移学习技术构建二类识别器(I-2-C和M-2-C)和八类识别器(I-8-C和M-8-C)。【结果】M-8-C模型的整体识别表现最优,对所有图像的识别准确率为93.7%,表明构建的神经网络识别器能有效辨别柑橘黄龙病症状;I-8-C和M-8-C对所有类型图像的平均F1分值分别为77.9%和88.4%,高于I-2-C(56.3%)和M-2-C(52.5%),表明症状细分有利于提高模型的识别能力。同时M-8-C比I-8-C略高的平均F1分值表明基于MobileNetV1结构的八类识别器识别表现略优于基于InceptionV3的八类识别器。基于M-8-C改进的识别器M-8f-C能够转移到智能手机上,在田间测试中取得较好的识别表现。【结论】基于深度学习和迁移学习开发的识别器对黄龙病单叶症状具有较好的识别效果。【Objective】To explore the capability of deploying deep learning to the detection of Huanglongbing(HLB)symptom in Citrus spp.,and evaluate the classification accuracies of the classifiers.【Method】Two-class classifiers(I-2-C and M-2-C)and eight-class classifiers(I-8-C and M-8-C)were constructed using images of diseased leaves caused by HLB/non-HLB and healthy leaves based on convolutional neural networks and transfer learning.【Result】The overall classification performance of M-8-C stood out in all classifiers with accuracy of 93.7%,implying great capability in deep convolutional neural networks for classifying HLB symptoms.The mean F1 socres of I-8-C and M-8-C were 77.9%and 88.4%respectively,which were higher than those of I-2-C(56.3%)and M-2-C(52.5%).This indicated that subtyping symptoms could help improve the recognition ability of models.The slightly higher mean F1 score of M-8-C compared with I-8-C indicated that the eight-class model based on MobileNetV1 had better performance than the one based on InceptionV3.An optimized model,namely M-8f-C,was developed based on M-8-C and was successfully mounted on mobile phone.The field tests showed that M-8f-C was of decent performance under field conditions.【Conclusion】Classifier based on deep learning and transfer learning has high accuracy for recognizing HLB symptom leaves.

关 键 词：柑橘黄龙病 症状识别 卷积神经网络 迁移学习 

分 类 号：S436.66[农业科学—农业昆虫与害虫防治]