[1]赵兵,冯全.基于全卷积网络的葡萄病害叶片分割[J].南京农业大学学报,2018,41(4):752-759.[doi:10.7685/jnau.201711021]
 ZHAO Bing,FENG Quan.Segmentation of grape diseases leaf based on full convolution network[J].Journal of Nanjing Agricultural University,2018,41(4):752-759.[doi:10.7685/jnau.201711021]
点击复制

基于全卷积网络的葡萄病害叶片分割()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
41卷
期数:
2018年4期
页码:
752-759
栏目:
出版日期:
2018-07-09

文章信息/Info

Title:
Segmentation of grape diseases leaf based on full convolution network
作者:
赵兵 冯全
甘肃农业大学机电工程学院, 甘肃 兰州 730070
Author(s):
ZHAO Bing FENG Quan
Mechanical and Electrical Engineering College, Gansu Agricultural University, Lanzhou 730070, China
关键词:
葡萄叶片光照复杂背景卷积神经网络全卷积网络自动分割病害
Keywords:
grape leaflightcomplex backgroundconvolution neural networkfull convolution networkautomatic segmentationdisease
分类号:
TP391.41
DOI:
10.7685/jnau.201711021
摘要:
[目的]本文旨在解决不同光照和复杂背景下葡萄病害叶片图像的自动分割。[方法]使用了一种全卷积网络(FCN)的葡萄病害叶片图像的自动分割算法。该算法在结构上将传统的卷积神经网络(CNN)后3个全连接层换成3个卷积层。通过多层的卷积,对输入葡萄叶片图像的特征进行提取;通过池化层,对特征信息进行筛选,缩减特征尺寸,以达到减少网络参数的目的。再通过反卷积对特征上采样,从高维、小尺寸特征恢复到图像原始尺寸,对具有原始尺寸的特征进行逐像素分类,确定原图像中每个像素位置的标签是背景还是前景。因只经过上采样处理后的分割图像会较粗糙,故通过跳跃结构将较为粗糙的原图进行局部信息与整体信息的整合,达到对分割结果进行精细化处理的目的。[结果]本算法对葡萄病害叶片有较好的分割效果,单叶片和复杂多叶片图像的马修斯相互系数(MCC)分别为0.821和0.747,MCC平均值较对比算法提高了6.5%。[结论]本算法能够较精确地分割自然条件下成像的葡萄病害叶片图像,为后续在叶片精准分割病害区域和提取病害特征创造了良好的条件。
Abstract:
[Objectives]The research aimed to solve the automatic segmentation of diseased grape leaf images under different light and cluttered background.[Methods]We used a full convolution network(FCN)to automatically segment the grape leaf images. The method replaced the last three full connection layers in a tradition convolution neural network(CNN)with three convolution layers. Through multiple convolution layers,the features of input of images were extracted. And by the pooling layers,feature sizes were reduced so the network parameters decreased. When the features were gotten,they were up-sampled with the de-convolution layers,restoring the original image size. The output was labeled background and foreground with pixel wise classifiers. However,the segmentation was kind of rough. So,two skipping structures were employed to get finer results by integrating the local information and whole information.[Results]The experimental results showed that the algorithm worked well in segmenting the grape leaves of diseases. The mathews mutual coefficient(MCC)achieved 0.821 and 0.747 for single leaf and multiple leaves,respectively. The average MCC improved 6.5% than the contrasted algorithm.[Conclusions]Due to the good performance of the proposed algorithm,it can create good conditions for the subsequent segmentation of the disease area in leaves and the extraction of disease features.

参考文献/References:

[1] 张芳,王璐,付立思,等. 复杂背景下黄瓜病害叶片的分割方法研究[J]. 浙江农业学报,2014,26(5):1346-1355. Zhang F,Wang L,Fu L S,et al. Segmentation method for cucumber disease leaf images under complex background[J]. Acta Agriculturae Zhejiangensis,2014,26(5):1346-1355(in Chinese with English abstract).
[2] 王献锋,张善文,王震,等. 基于叶片图像和环境信息的黄瓜病害识别方法[J]. 农业工程学报,2014,30(14):148-153. Wang X F,Zhang S W,Wang Z,et al. Recognition of cucumber diseases based on leaf image and envi ronmental information[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(14):148-153(in Chinese with English abstract).
[3] 刘媛,冯全. 葡萄病害的计算机识别方法[J]. 中国农机化学报,2017,38(4):99-104. Liu Y,Feng Q. Identification method of grape diseases based on computer technology[J]. Journal of Chinese Agricultural Mechanization,2017,38(4):99-104(in Chinese with English abstract).
[4] 王玉德,张学志. 复杂背景下甜瓜果实分割算法[J]. 农业工程学报,2014,30(2):176-181. Wang Y D,Zhang X Z. Segmentation algorithm of muskmelon fruit with complex background[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(2):176-181(in Chinese with English abstract).
[5] 刁智华,王欢,宋寅卯,等. 复杂背景下棉花病叶害螨图像分割方法[J]. 农业工程学报,2013,29(5):147-152. Diao Z H,Wang H,Song Y M,et al. Segmentation method for cotton mite disease image under complex background[J]. Transactions of the Chinese Society of Agricultural Engineering,2013,29(5):147-152(in Chinese with English abstract).
[6] 袁媛,李淼,吴娜,等. 黄瓜病害图像分割评价方法试验研究[J]. 农机化研究,2014(10):160-163. Yuan Y,Li M,Wu N,et al. Research on evaluation methods for image segmentation of cucumber disease[J]. Agricultural Mechanization Research,2014(10):160-163(in Chinese with English abstract).
[7] 刘志强,梁琨,沈明霞,等. 基于无线传感网络的植物生长图像传输和分割算法研究[J]. 南京农业大学学报,2014,37(4):170-176. DOI:10.7685/j.issn.1000-2030.2014.04.025. Liu Z Q,Liang K,Shen M X,et al. Research of plant growth image transmission based on wireless sensor network and segmentation algorithm[J]. Journal of Nanjing Agricultural University,2014,37(4):170-176(in Chinese with English abstract).
[8] Abdul-Nasir A S,Mashor M Y,Mohamed Z. Colour image segmentation approach for detection of malaria parasites using various colour models and K-means clustering[J]. Wseas Transactions on Biology and Biomedicine,2013,10(1):41-55.
[9] Guijarro M,Pajares G,Riomoros I,et al. Automatic segmentation of relevant textures in agricultural images[J]. Computers and Electronics in Agriculture,2011,75(1):75-83.
[10] Hashemi A B,Meybodi M R. A note on the learning automata based algorithms for adaptive parameter selection in PSO[J]. Applied Soft Computing,2011,11(1):689-705.
[11] 赵金阳.自然条件下葡萄叶片图像的自动分割方法研究[D]. 兰州:甘肃农业大学,2017. Zhao J Y. Research on automatic segmentation of grape leaf image under natural condition[D]. Lanzhou:Gansu Agricultural University,2017(in Chinese with English abstract).
[12] Long J,Shelhamer E,Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Patern Analysis and Machine Intelligence,2014,39(4):640-651.
[13] 程玉柱,陈勇,张浩.基于MMC与CV模型的苗期玉米图像分割算法[J]. 农业机械学报,2013,44(11):266-270. Cheng Y Z,Chen Y,Zhang H. Color image segmentation algorithm of corn based on MMC and CV model[J]. Transactions of the Chinese Society of Agricultural Machinery,2013,44(11):266-270(in Chinese with English abstract).
[14] 陈鸿翔. 基于卷积神经网络的图像语义分割[D]. 杭州:浙江大学,2016. Chen H X. Semantic segmentation based on convolutional neural networks[D]. Hangzhou:Zhejiang University,2016(in Chinese with English abstract).
[15] 吕力兢. 基于卷积神经网络的结肠病理图像中的腺体分割[D]. 南京:东南大学,2016. Lü L J. Gland segmention in colon histology images using the convolutional neural networks[D]. Nanjing:Southeast University,2016(in Chinese with English abstract).
[16] 李巧玲,关晴骁,赵险峰. 基于卷积神经网络的图像生成方式分类方法[J]. 网络与信息安全学报,2016,2(9):40-48. Li Q L,Guan Q X,Zhao X F.Image generation classification method based on convolution neural network[J]. Chinese Journal of Network and Information Security,2016,2(9):40-48(in Chinese with English abstract).
[17] 杨森,冯全,杨梅,等. 彩色叶片图像去尘算法[J]. 计算机辅助设计与图形学学报,2016,28(8):1224-1231. Yang S,Feng Q,Yang M,et al. An algorithm of dust removal for color leaves image[J]. Journal of Computer-Aided Design and Computer Grapahics,2016,28(8):1224-1231(in Chinese with English abstract).
[18] Zhang J,Huang M,Jin X,et al. A real-time chinese traffic sign detection algorithm based on modified YOLOv2[J]. Algorithms,2017,10(4):127.
[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 and Machine Intelligence,2017,39(6):1137-1149.
[20] Zhou J,Wang H,Zhao Z,et al. CNNH_PSS:protein 8-class secondary structure prediction by convolutional neural network with highway[J]. BMC Bioinformatics,2018,19(4):60.
[21] He K,Sun J,Tang X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[22] Siano P,Cecati C,Yu H,et al. Real time operation of smart grids via FCN networks and optimal power flow[J]. IEEE Transactions on Industrial Informatics,2012,8(4):944-952.
[23] Maheswari S,Jeya R,Rameshwaran K. BPN based segmentation of blood vessels in retinal images using combined filters[J]. International Journal of Applied Engineering Research,2015,10(20):15531-15536.
[24] 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 and Machine Intelligence,2018,40(4):834-848.

相似文献/References:

[1]蒋芳玲,徐磊,王克磊,等.光照与基质含水量对不结球白菜光合特性的影响[J].南京农业大学学报,2011,34(6):25.[doi:10.7685/j.issn.1000-2030.2011.06.005]
 JIANG Fang-ling,XU Lei,WANG Ke-lei,et al.Effects of light and water content in substrate on photosynthetic characteristics in non-heading Chinese cabbage(Brassica campestris ssp.chinensis Makino)[J].Journal of Nanjing Agricultural University,2011,34(4):25.[doi:10.7685/j.issn.1000-2030.2011.06.005]

备注/Memo

备注/Memo:
收稿日期:2017-11-12。
基金项目:国家自然科学基金项目(61461005)
作者简介:赵兵,硕士研究生。
通信作者:冯全,博士,教授,主要研究方向为信息处理与农业工程,E-mail:fquan@sina.com
更新日期/Last Update: 1900-01-01