Grade classification of wheat stripe rust disease based on deep learning

GUO Wei; DANG Mengjia; JIA Xiao; HE Qiang; GAO Chunfeng; DONG Ping

doi:10.7671/j.issn.1001-411X.202206033

Journal of South China Agricultural University > 2023 > 44(4): 604-612. > DOI: 10.7671/j.issn.1001-411X.202206033

GUO Wei, DANG Mengjia, JIA Xiao, et al. Grade classification of wheat stripe rust disease based on deep learning[J]. Journal of South China Agricultural University, 2023, 44(4): 604-612. DOI: 10.7671/j.issn.1001-411X.202206033

Citation:

PDF (2656 KB)

Grade classification of wheat stripe rust disease based on deep learning

College of Information and Management Science, Henan Agricultural University, Zhengzhou 450000, China

More Information

Received Date: June 23, 2022
Available Online: September 03, 2023
Published Date: March 08, 2023

Graphical Abstract

Abstract

Abstract

Objective
In order to improve the grade classification accuracy of damage degree by wheat stripe rust, the automatic, accurate and rapid identification method of damage degree by wheat stripe rust was studied.
Method
Under complex field conditions, images were taken by mobile phones, and data sets of wheat leaves with different grades of stripe rust were constructed. The combination of GrabCut and YOLOv5s was used to automatically segment wheat leaves from complex background. The Inception module was added to enhance the ability of ResNet50 in extracting phenotypic features. The disease grades of wheat stripe rust were identified according to the classified disease grade standards of wheat stripe rust. The performance of the improved ResNet50 model (B-ResNet50) on the data set was analyzed using evaluation indexes such as accuracy, recall and precision.
Result
Wheat leaf images were segmented automatically, accurately and quickly by the combination of GrabCut and YOLOv5s under complex background in the field. The recognition rate of B-ResNet50 on the data set of wheat stripe rust leaves was 97.3%, which was obviously higher than that of InceptionV3 (87.8%), DenseNet121 (87.6%) and ResNet50 (88.3%). The accuracy rate was greatly improved, and nine percentage points more than that of the original model(ResNet50).
Conclusion
Using deep learning to identify the disease grade of wheat stripe rust is of great significance to applying accurate pesticide for its control, and provides technical support for the control of wheat stripe rust under complex field conditions.
- Wheat stripe rust,
- Image segmentation,
- Deep learning,
- Disease grade,
- ResNet50,
- Precise spraying

FullText(HTML)

References (29)

References

[1]	张建莉. 小麦重大病虫害综合防治技术[J]. 乡村科技, 2019(34): 97-98. doi: 10.19345/j.cnki.1674-7909.2019.34.048
[2]	于静. 小麦条锈病综合治理理论探析[J]. 现代农业科技, 2020(9): 126. doi: 10.3969/j.issn.1007-5739.2020.09.077
[3]	吴海瑞. 小麦条锈病的发生及防治[J]. 农业技术与装备, 2021(8): 152-153. doi: 10.3969/j.issn.1673-887X.2021.08.071
[4]	冷伟锋, 王海光, 胥岩, 等. 无人机遥感监测小麦条锈病初探[J]. 植物病理学报, 2012, 42(2): 202-205. doi: 10.3969/j.issn.0412-0914.2012.02.013
[5]	SU J Y, LIU C J, HU X P, et al. Spatio-temporal monitoring of wheat yellow rust using UAV multispectral imagery[J]. Computers and Electronics in Agriculture, 2019, 167: 105035. doi: 10.1016/j.compag.2019.105035.
[6]	张竞成, 李建元, 杨贵军, 等. 基于光谱知识库的TM影像冬小麦条锈病监测研究[J]. 光谱学与光谱分析, 2010, 30(6): 1579-1585. doi: 10.3964/j.issn.1006-0593(2010)06-1579-07
[7]	马慧琴, 黄文江, 景元书, 等. 基于AdaBoost模型和mRMR算法的小麦白粉病遥感监测[J]. 农业工程学报, 2017, 33(5): 162-169. doi: 10.11975/j.issn.1002-6819.2017.05.024
[8]	余秀丽, 徐超, 王丹丹, 等. 基于SVM的小麦叶部病害识别方法研究[J]. 农机化研究, 2014, 36(11): 151-155. doi: 10.3969/j.issn.1003-188X.2014.11.036
[9]	许高建, 沈杰, 徐浩宇. 基于Lab颜色空间下的小麦赤霉病图像分割[J]. 中国农业大学学报, 2021, 26(10): 149-156. doi: 10.11841/j.issn.1007-4333.2021.10.15
[10]	陆海飞. 显著性检测方法及其在黄瓜病害图像分割中的应用研究[D]. 南京: 南京农业大学, 2016.
[11]	陈煜. 基于颜色特征的花生叶褐斑病及黑斑病图像识别技术研究[D]. 郑州: 河南大学, 2019.
[12]	BAKHSHIPOUR A, JAFARI A, NASSIRI S M, et al. Weed segmentation using texture features extracted from wavelet sub-images[J]. Biosystems Engineering, 2017, 157: 1-12. doi: 10.1016/j.biosystemseng.2017.02.002.
[13]	PULIDO ROJAS C, SOLAQUE GUZMÁN L,VELASCO TOLEDO N. Weed recognition by SVM texture feature classification in outdoor vegetable crops images[J]. Ingeniería e Investigación, 2017, 37(1): 68-74.
[14]	GRIFFEL L M, DELPARTE D, EDWARDS J. Using support vector machines classification to differentiate spectral signatures of potato plants infected with potato virus Y[J]. Computers and Electronics in Agriculture, 2018, 153: 318-324.
[15]	戴雨舒, 仲晓春, 孙成明, 等. 基于图像处理和Deeplabv3+模型的小麦赤霉病识别[J]. 中国农机化学报, 2021, 42(9): 209-215.
[16]	陈燕, 朱成宇, 胡小春, 等. 基于改进Unet的小麦茎秆截面参数检测[J]. 农业机械学报, 2021, 52(7): 169-176. doi: 10.6041/j.issn.1000-1298.2021.07.017
[17]	顾博, 邓蕾蕾, 李巍, 等. 基于GrabCut算法的玉米病害图像识别方法研究[J]. 中国农机化学报, 2019, 40(11): 143-149.
[18]	孔英会, 朱成诚, 车辚辚. 复杂背景下基于MobileNets的花卉识别与模型剪枝[J]. 科学技术与工程, 2018, 18(19): 84-88. doi: 10.3969/j.issn.1671-1815.2018.19.013
[19]	许景辉, 邵明烨, 王一琛, 等. 基于迁移学习的卷积神经网络玉米病害图像识别[J]. 农业机械学报, 2020, 51(2): 230-236. doi: 10.6041/j.issn.1000-1298.2020.02.025
[20]	刘阗宇, 冯全, 杨森. 基于卷积神经网络的葡萄叶片病害检测方法[J]. 东北农业大学学报, 2018, 49(3): 73-83. doi: 10.3969/j.issn.1005-9369.2018.03.009
[21]	龙满生, 欧阳春娟, 刘欢, 等. 基于卷积神经网络与迁移学习的油茶病害图像识别[J]. 农业工程学报, 2018, 34(18): 194-201. doi: 10.11975/j.issn.1002-6819.2018.18.024
[22]	PICON A, SEITZ M, ALVAREZ-GILA A, et al. Crop conditional convolutional neural networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions[J]. Computers and Electronics in Agriculture, 2019, 167:105093. doi: 10.1016/j.compag.2019.105093.
[23]	CHEN J D, CHEN J X, ZHANG D F, et al. Using deep transfer learning for image-based plant disease identification[J]. Computers and Electronics in Agriculture, 2020, 173:105393. doi: 10.1016/j.compag.2020.105393.
[24]	中国农业科学院植物保护研究所. 小麦抗条锈病评价技术规范: 小麦抗病虫性评价技术规范第1部分: NY/T 1443.1—2007[S]. 北京: 中华人民共和国农业部.
[25]	ROTHER C. "GrabCut": Interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics (TOG), 2004, 23(3): 309-314.
[26]	SRIVASTAVA R K, GREFF K, SCHMIDHUBER J. Training very deep networks[R/OL]. arXiv: https://doi.org/10.48550/arXiv.1512.03385, 2015.
[27]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[R/OL]. arXiv: https://doi.org/10.48550/arXiv.1512.03385, 2016.
[28]	ZHANG K, ZUO W, CHEN Y, et al. Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2016, 26(7): 3142-3155.
[29]	ZHENG Y, WANG R, YANG J, et al. Principal characteristic networks for few-shot learning[J]. Journal of Visual Communication and Image Representation, 2019, 59(2): 563-573.

[1]	FU Han, WU Zhizhi, DUAN Jieli, YU Shaozheng, LIU Feng, ZHENG Haile. Calibration of contact parameters of ‘Luli’ apple for simulation based on discrete element[J]. Journal of South China Agricultural University, 2025, 46(3): 407-418. DOI: 10.7671/j.issn.1001-411X.202403013
[2]	CUI Guangjuan, CAO Huayuan, CHEN Kang, WANG Xiurong. Effects of cadmium stress on plant growth and element distribution of four soybean genotypes[J]. Journal of South China Agricultural University, 2020, 41(5): 49-57. DOI: 10.7671/j.issn.1001-411X.201911023
[3]	XIA Hongmei, XIA Juan, ZHEN Wenbin, ZHANG Bingchao. Design and test of a contact mechanics model for papaya picking[J]. Journal of South China Agricultural University, 2017, 38(3): 99-105. DOI: 10.7671/j.issn.1001-411X.2017.03.016
[4]	Lü Yan-qing, XIE Mei-qiong, HE Yu-rong, CHEN Ke-wei. Contact Response of Trichogrammatoidea bactrae to Different Components of Kairomones of Plutella xylostella[J]. Journal of South China Agricultural University, 2011, 32(2): 30-34. DOI: 10.7671/j.issn.1001-411X.2011.02.007
[5]	HU Chuan-shuang,LI Chong-gen,LIA Hong-xia,LU Qun-xia,YUN Hong. Modeling the Wind Pressure Distribution on a Prefabricated Wood Framing Structure During High-Speed Transportation[J]. Journal of South China Agricultural University, 2008, 29(2): 112-114. DOI: 10.7671/j.issn.1001-411X.2008.02.027
[6]	HUANG Tian-fu,XIONG Zhong-hua,ZENG Xin-nian. Studies on the Contact Toxicity of Insecticides Against the Worker Ants of Solenopsis invicta[J]. Journal of South China Agricultural University, 2007, 28(4): 26-29. DOI: 10.7671/j.issn.1001-411X.2007.04.007
[7]	YI Qi-fei,XING Fu-wu,CHEN Hong-feng,HUANG Xiang-xu. Distribution and utilization of Pholidota in China[J]. Journal of South China Agricultural University, 2004, 25(3): 94-97. DOI: 10.7671/j.issn.1001-411X.2004.03.025
[8]	DENG Ye-cheng,XU Han-hong,LEI Ling. Contact toxicity of extracts from leaf and exopleura of Ginkgo biloba to pest insects[J]. Journal of South China Agricultural University, 2004, 25(3): 61-63. DOI: 10.7671/j.issn.1001-411X.2004.03.017
[9]	LI Kai fu,GAO Zhen zhong,SUN Jin. Study of Particleboard Wet Stress[J]. Journal of South China Agricultural University, 2001, 22(3): 83-85,89. DOI: 10.7671/j.issn.1001-411X.2001.03.026
[10]	LI Kaifu,GAO Zhenzhong,SUN Jin. Study on the Heat Stress of Particleboard[J]. Journal of South China Agricultural University, 2001, 22(1): 81-84. DOI: 10.7671/j.issn.1001-411X.2001.01.025

Cited By

Cited by

Periodical cited type(2)

1.	徐慧娟，邝智祥，左珂菁，吴承洋，郑泓昊，谢青梅，陈伟国. tva受体基因起始密码子突变对清远麻鸡感染K亚群禽白血病病毒的影响. 华南农业大学学报. 2025(03): 351-357 . 本站查看
2.	郑文静，田亚东，李转见，李东华. 禽白血病抗病育种研究进展. 中国畜禽种业. 2024(01): 42-46 .

Other cited types(0)

Get Citation

PDF

XML

Article views (736) PDF downloads (26) Cited by(2)

Turn off MathJax

Article Contents

Abstract

References

Grade classification of wheat stripe rust disease based on deep learning