基于2D DWT与MobileNetV3融合的轻量级茶叶病害识别  

Recognizing tea diseases with fusion on 2D DWT and MobileNetV3

作　　者：黄铝文[1,2] 关非凡 谦博 侯闳耀 刘迎庆 李雯敏 HUANG Lyuwen;GUAN Feifan;QIAN Bo;HOU Hongyao;LIU Yingqing;LI Wenmin(College of Information Engineering,Northwest A&F University,Yangling 712100,China;Shaanxi Engineering Research Center for Intelligent Perception and Analysis of Agricultural Information,Yangling 712100,China;College of Horticulture,Northwest A&F University,Yangling 712100,China)

机构地区：[1]西北农林科技大学信息工程学院,杨凌712100 [2]陕西省农业信息智能感知与分析工程技术研究中心,杨凌712100 [3]西北农林科技大学园艺学院,杨凌712100

出　　处：《农业工程学报》2023年第24期207-214,共8页Transactions of the Chinese Society of Agricultural Engineering

基　　金：陕西省重点研发计划(一般农业项目)农作物病虫快速诊断研究与预警系统应用(2023-YBNY-219)。

摘　　要：针对现有茶叶病害识别方法病害信息挖掘不足导致识别准确率低的问题,该研究提出了一种基于二维离散小波变换(discrete wavelet transform, DWT)和MobileNetV3融合的茶叶病害识别模型CBAM-TealeafNet。为增强网络对病害频域特征的检测能力,将2D DWT获取的频域特征与bneck结构提取的深度特征融合,形成频域与深度特征融合的识别网络。为提高特征提取能力,在bneck结构中,嵌入卷积块注意模块(convolutional block attention module, CBAM),为特征通道分配相应权重。为解决样本类别不平衡对识别模型性能的影响,利用焦点损失函数取代交叉熵损失函数以提高识别精度。经验证,CBAM-TealeafNet在5种不同茶叶病害上整体识别准确率达到98.70%,参数量为3.16×10^(6),相对MobileNetV3,准确率提升2.15个百分点,参数量降低25.12%。该方法可为茶树叶部等作物病害轻量级识别研究提供模型参考。Diseases have posed the serious threaten on the yield and quality of tea production.An accurate and rapid recognition of leaf diseases is essential to the instant diseases prevention of tea plantation.Deep learning can be expected to realize a rapid and accurate identification of tea diseases in natural environment with the advantages of low cost and high efficiency,compared with typical disease diagnosis.However,the previous models have much more parameters and computational complexity for the leaf diseases diagnosis.Furthermore,the lightweight models cannot fully meet the finegrained feature extraction.In this study,a disease recognition network(CBAM-TealeafNet)was proposed to extract the frequency features by the 2D discrete wavelet transform(2D DWT)and depth features by the bneck structure.Frequency features were then decomposed to suppress the high-frequency components.The fused feature module was used to reduce the impact of noise on the features for the features enhancement.CBAM(convolutional block attention module)was embedded to improve the feature extraction capability in the bneck structure.The weights were allocated into the feature channels and spatial position features of diseases.The function of focal loss was employed to replace the primitive cross-entropy loss,in order to better resolve the imbalance influences on sample class for the high accuracies.Totally,3,260 disease images of Shaanxi Tea No.1 and Longjing No.43 were captured,including five tea disease categories:gloeosporium theae-sinensis miyake,colletotrichum camelliae massee,cercospora theae breadade haan,exobasidium vexans masse,and phyllosticta theicola petch.The real environment was also simulated to evaluate the datasets.The images were then enhanced.Experiments were carried out to validate the optimal model structure and the improvement analysis of each component.The model was optimized for the hyperparameters setting.The final optimal learning rate was 0.0005,which was derived from an initial learning rate range of 0.00005-0.005.In

关 键 词：病害 图像识别 茶 2D DWT 特征融合 CBAM 焦点损失 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S24[自动化与计算机技术—计算机科学与技术]