基于U-net和可见光谱图像的黄瓜褐斑病分割  

Segmentation of Cucumber Target Leaf Spot Based on U-Net and Visible Spectral Images

作　　者：王翔宇 李海生 吕丽君[1] 韩丹枫 王梓强 WANG Xiang-yu;LI Hai-sheng;LV Li-jun;HAN Dan-feng;WANG Zi-qiang(Department of Electronic Information and Physics,Changzhi University,Changzhi 046011,China;Industrial Technology Center,Chengde Petroleum College,Chengde 067000,China)

机构地区：[1]长治学院电子信息与物理系,山西长治046011 [2]承德石油高等专科学校工业技术中心,河北承德067000

出　　处：《光谱学与光谱分析》2021年第5期1499-1504,共6页Spectroscopy and Spectral Analysis

基　　金：山西省高等学校科技创新项目(2019L0907);国家自然科学基金项目(31271618)资助。

摘　　要：褐斑病是黄瓜主要真菌性病害之一,适宜条件下,特别是在昼夜温差大及饱和湿度条件下发病迅速,病情加重,导致黄瓜减产,造成经济损失。对黄瓜褐斑病进行病斑分割与提取,可以为后续的病害识别与诊断提供有效依据,具有重要意义。结合黄瓜褐斑病可见光谱图像,利用U-net深度学习网络构建黄瓜褐斑病语义分割模型,实现了病斑分割。首先在采集到的黄瓜褐斑病可见光谱图像中截取病斑较为突出的区域作为样本,共在40幅图像中截取到135个像素区域,区域的像素分辨率为200×200,利用Matlab的Image Label er工具对样本进行像素标记,分别标记出感病区域和健康区域。然后构建U-net网络,该网络包含46层和48个连接,通过卷积层和线性整流层以及最大池化法来完成病斑特征提取,通过深度连接层以及上卷积层和上线性整流层完成上采样,通过跳层连接来完成复制和剪裁操作,并进行病斑特征融合。利用所构建的U-net网络进行学习训练得到语义分割模型,在135个样本中,随机选取其中96个作为训练样本,剩余的39个作为测试样本,设置迭代次数为240次,L2正则化系数为0.0001,初始学习率为0.05,动量参数为0.9,梯度阈值为0.05,进行样本训练和测试。经过10次重复训练和测试,结果表明,基于U-net和可见光谱图像的黄瓜褐斑病语义分割模型执行时间平均为46.4 s,内存占用平均为6665.8 MB,执行效率较高;模型准确率PA为96.23%~97.98%,MPA为97.28%~97.87%,MIoU为86.10%~91.59%,FWIoU为93.33%~96.19%,模型的稳定性较好、泛化能力较强。该研究方法利用较少的训练样本,获得了准确率较高的分割模型,为小样本机器学习提供了参考,同时为其他蔬菜的病斑分割、病害识别与诊断提供了方法依据。Target leaf spot is one of the main fungous diseases of cucumber.Under suitable conditions,especially under the conditions of the large temperature difference between day and night or saturated humidity,the disease develops rapidly,leads to the reduction of cucumber yield and brings economic losses.The cucumber target leaf spot segmentation can provide an effective basis for the identification and diagnosis of cucumber disease,which has great significance.In this study,a cucumber spectral image was taken as the research object,and U-net deep learning network was utilized to construct the semantic segmentation model for cucumber target leaf spot segmentation.Firstly,the regions with more prominent lesions in the visible spectrum images were selected for training and testing.We captured 135 regions out of 40 images as samples,and each region was 200×200 pixel.The Image labeler tool of Matlab was used to label the samples to mark the affected area and the healthy area.Then,the U-net network was constructed,which contains 46 layers and 48 connections.The cucumber target leaf spots’feature extraction is completed by convolution layer,ReLU layer and max-pooling.The upsampling is completed by deep connection layer,up convolution layer and up-ReLU.The copy and crop operations and feature fusion are completed by skip connection.The U-net was used for training to get the semantic segmentation model.From 135 samples,96 were randomly selected as training samples and the remaining 39 as test samples.Set the iterations 240,L2 regularization coefficient 0.0001,initial learning rate 0.05,momentum parameter 0.9,gradient threshold 0.05,and then utilize the samples for training and testing.After 10 repeated training and testing,the results showed that the average execution time of the semantic segmentation model based on U-net and visible spectrum images was 46.4 s.The average memory occupation was 6665.8 MB,and it shows that the model has a high execution efficiency.The pixel accuracy of the model was 96.23%~97.98%,mean pixel a

关 键 词：U-net网络 可见光谱 黄瓜褐斑病 深度学习 语义分割 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]