[1]王振,张善文,王献锋.基于改进全卷积神经网络的黄瓜叶部病斑分割方法[J].江苏农业学报,2019,(05):1054-1060.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
　WANG Zhen,ZHANG Shan-wen,WANG Xian-feng.Method for segmentation of cucumber leaf lesions based on improved full convolution neural network[J].,2019,(05):1054-1060.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
点击复制

基于改进全卷积神经网络的黄瓜叶部病斑分割方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年05期
页码:
1054-1060
栏目:
植物保护
出版日期:
2019-10-31

文章信息/Info

Title:
Method for segmentation of cucumber leaf lesions based on improved full convolution neural network
作者:
王振; 张善文; 王献锋
(西京学院信息工程学院，陕西西安710123)
Author(s):
WANG Zhen;  ZHANG Shan-wen;  WANG Xian-feng
(College of Information Engineering, Xijing University, Xi′an 710123, China)
关键词:
黄瓜病斑图像; 卷积神经网络; 激活函数; 图像分割
Keywords:
cucumber lesion image;  convolution neural network;  activation function;  image segmentation
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2019.05.008
文献标志码:
A
摘要:
为了解决传统卷积神经网络在黄瓜叶部病斑图像分割中存在模型训练时间长、分割效果差以及分割过程中易受光照和背景影响等问题，提出了一种基于改进全卷积神经网络的黄瓜叶部病斑分割方法。首先在模型训练的初始阶段使用传统的卷积神经网络得到病斑图像的轮廓特征，在训练过程中将传统的修正性单元(RELU)激活函数替换为指数线性单元(ELU)激活函数；然后对传统的卷积神经网络得到的病斑图像轮廓特征进行二次模型训练，训练过程中使用批归一化(Batch normalization)函数稳定模型训练过程；最后将原始卷积神经网络的多项逻辑回归(Soft max)分类器更换为支持向量机(SVM)分类器，对分类器输出的像素分类结果进行反卷积操作，恢复图像分辨率，得到分割结果。使用本研究方法与改进OTSU、SVM、CRF和传统FCN等4种方法在黄瓜叶部病斑数据集上进行分割试验，结果表明本研究方法的平均像素分割准确率为80.46%，平均交并比为70.43%，具有较高的分割精度。
Abstract:
To solve the problems of the traditional convolutional neural network(CNN) in the process of cucumber leaf diseases image segmentation, such as long model training time, poor segmentation effect and easy to be affected by light and background in the process of segmentation, a method for segmentation of cucumber leaf diseases based on improved fully convolutional neural network was proposed. Firstly, in the initial stage of model training, traditional CNN was used to obtain the contour features of the diseases image. In the process of training, activation function of rectified linear units (RELU) was replaced by the exponential linear unit (ELU). Secondly, the disease contour features obtained by the traditional CNN were trained twice, and the batch normalization function was used to stabilize the model training process. Finally, the SoftMax of the original CNN was replaced with support vector machine(SVM), and the pixel classification result outputs by the classifier were deconvolution operation to restore the image resolution and obtain the segmentation results. The segmentation experiment was carried out on the cucumber leaf image by using this research algorithm and others four algorithms including improved OTSU, SVM, CRF and traditional FCN. The results showed that the average pixel segmentation accuracy of this algorithm was 80.46%, and the average intersection ratio was 70.43%, which could accurately segment the diseased parts in the leaves.

参考文献/References:

[1]刘国奇, 邓铭, 李晨静. 融合RGB颜色空间的植物图像分割模型[J]. 郑州大学学报(理学版), 2019, 51(1):21-26.
[2]关强,薛河儒,姜新华.基于二维OTSU的田间植物图像分割方法[J].江苏农业科学,2015,43(12):437-440.
[3]赵金阳,冯全,王书志,等.一种改进的葡萄叶片自动分割算法[J].中国农业大学学报,2017,22(11):140-147.
[4]张会敏,谢泽奇,张善文,等.基于WT-OTSU算法的植物病害叶片图像分割方法[J].江苏农业科学,2017,45(18):194-196.
[5]张善文,张晴晴,齐国红,等.基于改进K中值聚类的苹果病害叶片分割方法[J].江苏农业科学,2017,45(18):205-208.
[6]刘立波,程晓龙,赖军臣. 基于改进全卷积网络的棉田冠层图像分割方法[J]. 农业工程学报,2018,34(12):193-201.
[7]段凌凤,熊雄,刘谦,等.基于深度全卷积神经网络的大田稻穗分割[J].农业工程学报,2018,34(12):202-209.
[8]马浚诚,杜克明,郑飞翔,等.基于卷积神经网络的温室黄瓜病害识别系统[J].农业工程学报,2018,34(12):186-192.
[9]FERREIRA A D S, FREITAS D M, SILVA G G D, et al. Weed detection in soybean crops using ConvNets [J]. Computers and Electronics in Agriculture, 2017, 143: 314-324.
[10]DECHANT C, WIESNER-HANKS T, CHEN S, et al. Automatedidentification of northern leaf blight-infected maize plants from field imagery using deep learning [J]. Phytopathology, 2017,107: 1426-1432.
[11]DING W, TAYLOR G. Automatic moth detection from trap images for pest management [J]. Computers and Electronics in Agriculture, 2016, 123: 17-28.
[12]LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4):640-651.
[13]ALEX K, ILYA S, GEOFFREY E H. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 1097-1105.
[14]GHOSAL S, BLYSTONE D, SINGH A K, et al. An explainable deep machine vision framework for plant stress phenotyping [J]. Proceedings of the National Academy of Sciences, 2018, 115(18):4613-4618.
[15]BAI X, LI X, FU Z, et al. A fuzzy clustering segmentation method based on neighborhood grayscale information for defining cucumber leaf spot disease images [J]. Computers and Electronics in Agriculture, 2017, 136: 157-165
[16]CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018, 40(4):834-848.
[17]于洪涛,袁明新,谢丰,等.一种融合动态OTSU和几何特征的苹果视觉分割算法[J].信息技术,2018,42(8):39-43.
[18]杨信廷,刘蒙蒙,许建平,等.自动监测装置用温室粉虱和蓟马成虫图像分割识别算法[J].农业工程学报,2018,34(1):164-170.
[19]REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.

相似文献/References:

[1]张善文,谢泽奇,张晴晴.卷积神经网络在黄瓜叶部病害识别中的应用[J].江苏农业学报,2018,(01):56.[doi:doi:10.3969/j.issn.1000-4440.2018.01.008]
　ZHANG Shan-wen,XIE Ze-qi,ZHANG Qing-qing.Application research on convolutional neural network for cucumber leaf disease recognition[J].,2018,(05):56.[doi:doi:10.3969/j.issn.1000-4440.2018.01.008]
[2]杨晋丹,杨涛,苗腾,等.基于卷积神经网络的草莓叶部白粉病病害识别[J].江苏农业学报,2018,(03):527.[doi:doi:10.3969/j.issn.1000-4440.2018.03.007]
　YANG Jin-dan,YANG Tao,MIAO Teng,et al.Recognition of powdery mildew disease of strawberry leaves based on convolutional neural network[J].,2018,(05):527.[doi:doi:10.3969/j.issn.1000-4440.2018.03.007]
[3]丁承君,刘强,田军强,等.信息物理系统事件驱动下的农业气象监测系统[J].江苏农业学报,2018,(04):825.[doi:doi:10.3969/j.issn.1000-4440.2018.04.016]
　DING Cheng-jun,LIU Qiang,TIAN Jun-qiang,et al.Agro-meteorological monitoring system based on event-driven modeling of cyber-physical system[J].,2018,(05):825.[doi:doi:10.3969/j.issn.1000-4440.2018.04.016]
[4]许伟栋,赵忠盖.基于卷积神经网络和支持向量机算法的马铃薯表面缺陷检测[J].江苏农业学报,2018,(06):1378.[doi:doi:10.3969/j.issn.1000-4440.2018.06.025]
　XU Wei-dong,ZHAO Zhong-gai.Potato surface defects detection based on convolution neural networks and support vector machine algorithm[J].,2018,(05):1378.[doi:doi:10.3969/j.issn.1000-4440.2018.06.025]
[5]孙云云,江朝晖,董伟,等.基于卷积神经网络和小样本的茶树病害图像识别[J].江苏农业学报,2019,(01):48.[doi:doi:10.3969/j.issn.1000-4440.2019.01.007]
　SUN Yun-yun,JIANG Zhao-hui,DONG Wei,et al.Image recognition of tea plant disease based on convolutional neural network and small samples[J].,2019,(05):48.[doi:doi:10.3969/j.issn.1000-4440.2019.01.007]
[6]徐岩,刘林,李中远,等.基于卷积神经网络的玉米品种识别[J].江苏农业学报,2020,(01):18.[doi:doi:10.3969/j.issn.1000-4440.2020.01.003]
　XU Yan,LIU Lin,LI Zhong-yuan,et al.Recognition of maize varieties based on convolutional neural network[J].,2020,(05):18.[doi:doi:10.3969/j.issn.1000-4440.2020.01.003]
[7]张善文,邵彧,齐国红,等.基于多尺度注意力卷积网络的作物害虫检测[J].江苏农业学报,2021,(03):579.[doi:doi:10.3969/j.issn.1000-4440.2021.03.005]
　ZHANG Shan-wen,SHAO Yu,QI Guo-hong,et al.Crop pest detection based on multi-scale convolutional network with attention[J].,2021,(05):579.[doi:doi:10.3969/j.issn.1000-4440.2021.03.005]
[8]袁红春,王敏,刘慧,等.基于特征交互与卷积网络的渔场预测模型[J].江苏农业学报,2021,(06):1501.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
　YUAN Hong-chun,WANG Min,LIU Hui,et al.Fishing ground prediction model based on feature interaction and convolutional network[J].,2021,(05):1501.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
[9]李婕,李毅,张瑞杰,等.无人机遥感影像在油菜品种识别中的应用[J].江苏农业学报,2022,38(03):675.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
　LI Jie,LI Yi,ZHANG Rui-jie,et al.Application of UAV remote sensing image in rape variety identification[J].,2022,38(05):675.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
[10]翟先一,魏鸿磊,韩美奇,等.基于改进YOLO卷积神经网络的水下海参检测[J].江苏农业学报,2023,(07):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]
　ZHAI Xian-yi,WEI Hong-lei,HAN Mei-qi,et al.Underwater sea cucumber identification based on improved YOLO convolutional neural network[J].,2023,(05):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]

备注/Memo

备注/Memo:
收稿日期：2019-02-14 基金项目：国家自然科学基金项目(61473237) 作者简介：王振(1994-),男，河南周口人，硕士研究生，研究方向为模式识别技术在农业领域的应用。(E-mail)wangzhen4013@163.com
更新日期/Last Update: 2019-11-11