摘要
为提高葡萄叶片病害图像中病斑分割性能,提出了一种基于显著性目标检测的病斑分割方法。采用显著性目标检测网络来生成葡萄病害叶片图像的显著性图,通过多种分辨率的网格结构提取图像局部和全局信息,并将它们融合成预测特征;再对病害叶片的显著性图用自适应阈值法分割出叶片上的病害区域,并用形态学方法进行后处理。结果表明,在测试集A上,所建立的方法对病斑分割性能指标马修斯相关系数(MCC)为0.625,略低于对比算法全卷积神经网络(FCN)的0.689,但在衡量泛化性能的测试集B上,所建立方法的MCC为0.338,远高于FCN的0.072,说明所建立方法在分割精度和泛化性方面具有较好的平衡性。
To improve the quality of lesion segmentation in leaf images with clutter background and uneven lighting,a novel method was presented based deep salient object detection.Saliency target detection network was used to generate the saliency map of grape disease leaf image.The local and global information of the image were extracted by multi-resolution grid structure and fused into prediction features.Then,the diseased areas on the leaves were segmented by the adaptive threshold method on the significance map of diseased leaves,and the post-processing was carried out by the morphological method.The segmentation experimental results show that,on the test set A,the Matthews correlation coefficient(MCC)of the proposed method is 0.625,which is slightly lower than 0.689 for the convolutional neural network comparison algorithm(FCN)of.On the test set B,the MCC for the proposed method is 0.338,much higher than 0.072 for the FCN.It shows that the proposed method has good balance between the segmentation accuracy and generalization.
作者
王书志
乔虹
冯全
张建华
WANG Shuzhi;QIAO Hong;FENG Quan;ZHANG Jianhua(College of Electrical Engineering,Northwest Minzu University,Lanzhou,Gansu 730030,China;School of Mechanical and Electrical Engineering,Gansu Agricultural University,Lanzhou,Gansu 730070,China;Agricultural Information Institute,Chinese Academy of Agricultural Sciences,Beijing 100081,China)
出处
《湖南农业大学学报（自然科学版）》
CAS
CSCD
北大核心
2021年第1期101-107,共7页
Journal of Hunan Agricultural University(Natural Sciences)
基金
国家自然科学基金项目(31971792)
中央高校基本科研业务费项目(31920200043)。
关键词
葡萄叶片病害
分割
显著性目标检测
grape leaf disease
segmentation
salient object detection
