Research and Application of Intelligent Recognition Method of Peach Tree Diseases Based on AI

doi:10.13304/j.nykjdb.2021.0935

Abstract

Abstract:

In order to solve the problems of low efficiency， high cost and low accuracy of traditional methods of manually identifying peach tree diseases， an intelligent recognition method of peach tree diseases based on AI deep learning was proposed. Using and fine-tuning the DenseNet-169 classification model pre-trained by ImageNet， data preprocessing and model training were performed on the image of 11 common diseases of peach trees， then the web terminal was built to integrate and develop a software system for intelligent recognition of peach tree diseases. The average recognition rate of these 11 peach tree diseases was over 91% by this method. Using image recognition technology to automatically identify peach tree diseases， combined with modern science and technology such as image processing， deep learning， data mining and analysis， the intelligent diagnosis and prevention suggestions for peach tree diseases were realized. This proposed method could reduce labor costs， simplify operations， and improve recognition efficiency， so it was conducive to timely diagnosis and decision-making for prevention and treatment of diseases. Therefore， this research had important significance and application value for promoting the intelligent management of orchard disease controling， and provided support for the research and practice of image recognition methods based on deep learning with small sample sets.

Key words: peach diseases, image recognition, deep learning, DenseNet model

摘要：

为解决传统人工识别桃树病害效率低、成本高、准确率低等问题，提出了基于AI深度学习的桃树病害智能识别方法，利用并微调ImageNet预训练的DenseNet-169分类模型，对桃树常见的11种病害图像进行预处理与模型训练，搭建桃树病害智能识别软件环境。该方法对常见桃树病害的平均识别率达到91%以上，结合图像处理、深度学习、数据挖掘等技术自动对桃树病害进行识别，实现桃树病害的智能诊断并提供防治建议。该方法具有人力成本低、操作简单、识别效率高等优点，利于病害的及时诊出与防治决策的制定，对促进果园病害防控的智慧化管理具有重要研究意义与应用价值。

关键词: 桃树病害, 图像识别, 深度学习, DenseNet模型

CLC Number:

S126

Jianwei WU, Jie HUANG, Xiaofei XIONG, Han GAO, Xiangyang QIN. Research and Application of Intelligent Recognition Method of Peach Tree Diseases Based on AI[J]. Journal of Agricultural Science and Technology, 2022, 24(5): 111-118.

吴建伟, 黄杰, 熊晓菲, 高晗, 秦向阳. 基于AI的桃树病害智能识别方法研究与应用[J]. 中国农业科技导报, 2022, 24(5): 111-118.

Figures/Tables 7

References 31

1	毕金峰,吕健,刘璇,等.国内外桃加工科技与产业现状及展望[J].食品科学技术学报, 2019,37(5):7-15.
	BI J F, LU J, LIU X, et al.. Research on techniques and industry situation and prospect for peach processing in domestic and aboard [J]. J. Food Sci. Technol., 2019,37(5):7-15.
2	朱更瑞.我国桃产业转型升级的思考[J].中国果树,2019(6):6-11.
	ZHU G R. Insights into transformation and upgrading of peach industry in China [J]. China Fruits, 2019 (6):6-11.
3	马革农,李建勋,张相斌,等.桃树病虫害防治中存在的问题及对策[J].现代农村科技, 2021(3):29-30.
4	刘圣华.果树病虫害的识别方法及防治策略[J].农业与技术, 2017,37(19):54,70.
	LIU S H. Identification methods and control strategies of fruit tree diseases and pests [J]. Agric. Technol., 2017,37(19):54,70.
5	朱伊平,管孝锋,黄海龙,等.农业病虫害远程诊断平台[J].浙江农业科学, 2020,61(09):1819-1820, 1832.
	ZHU Y P, GUAN X F, HUANG H L, et al. Research on remote diagnosis platform of agricultural diseases and insect pests [J]. J. Zhejiang Agric. Sci., 2020,61(9):1819-1820, 1832.
6	张嫚嫚,张武,金秀,等.农作物病虫害专家系统中的知识表示方法[J].江汉大学学报(自然科学版), 2019,47(4):378-384.
	ZHANG M M, ZHANG W, JIN X, et al. Knowledge representation methods of expert systems for crop pests and diseases [J]. J. Jianghan Univ. (Nat. Sci.), 2019,47(4):378-384.
7	赵春江.对发展农业智能科技的思考[J].机器人产业, 2020,(4):36-40.
	ZHAO C J. Thinking on the development of agricultural intelligent science and technology [J]. Robot Ind., 2020,(4):36-40.
8	张宇,王翠宁,秦妮妮.优化识别植物病虫害的方法[J].种子科技, 2020,38(7):77-78.
	ZHANG Y, WANG C N, QIN N N. Methods for optimizing identification of plant diseases and insect pests [J]. Seed Sci. Technol., 2020,38(7):77-78.
9	康飞龙,李佳,刘涛,等.多类农作物病虫害的图像识别应用技术研究综述[J].江苏农业科学, 2020,48(22):22-27.
	KANG F L, LI J, LIU T, et al.. Application technology of image recognition for various crop diseases and insect pests: a review [J]. Jiangsu Agric. Sci., 2020,48(22):22-27.
10	饶晓燕,吴建伟,李春朋,等.智慧苹果园“空-天-地”一体化监控系统设计与研究[J].中国农业科技导报, 2021,23(6):59-66.
	RAO X Y, WU J W, LI C P, et al. Design and research on “space-air-ground” integrated monitoring system for intelligent orchard [J]. J. Agric. Sci. Technol., 2021,23(6):59-66.
11	李素,郭兆春,王聪,等.信息技术在农作物病虫害监测预警中的应用综述[J].江苏农业科学, 2018,46(22):1-6.
	LI S, GUO Z C, WANG C, et al. Application of information technology in monitoring and early warning of crop diseases and insect pests [J]. Jiangsu Agric. Sci., 2018,46(22):1-6.
12	李禾.AI变身农业“医生”问诊作物病虫害[J].当代农机, 2018(12):20-21.
	LI H. AI turns into an agricultural “doctor” to inquire about crop diseases and pests [J]. Contemporary Farm Machinery, 2018(12):20-21.
13	王彦翔,张艳,杨成娅,等.基于深度学习的农作物病害图像识别技术进展[J].浙江农业学报, 2019,31(4):669-676.
	WANG Y X, ZHANG Y, YANG C Y, et al. Advances in new nondestructive detection and identification techniques of diseases based on deep learning [J]. Acta Agric. Zhejiangensis, 2019,31(4):669-676.
14	康飞龙,李佳,刘涛,等.多类农作物病虫害的图像识别应用技术研究综述[J].江苏农业科学, 2020,48(22):22-27.
	KANG F L, LI J, LIU T, et al. Application technology of image recognition for various crop diseases and insect pests: a review [J]. Jiangsu Agric. Sci., 2020,48(22):22-27.
15	边柯橙,杨海军,路永华.深度学习在农业病虫害检测识别中的应用综述[J].软件导刊, 2021,20(3):26-33.
	BIAN K C, YANG H J, LU Y H. Application review of deep learning in detection and identification of agricultural pests and diseases [J]. Software Guide, 2021,20(3):26-33.
16	周惠汝,吴波明.深度学习在作物病害图像识别方面应用的研究进展[J].中国农业科技导报, 2021,23(5):61-68.
	ZHOU H R, WU B M. Advances in research on deep learning for crop disease image recognition [J]. J. Agric. Sci. Technol., 2021,23(5):61-68.
17	盖荣丽,蔡建荣,王诗宇,等.卷积神经网络在图像识别中的应用研究综述[J].小型微型计算机系统, 2021,42(9):1980-1984.
	GAI L R, CAI J R, WANG S Y, et al.. Research review on image recognition based on deep learning [J]. J. Chin. Computer Sys., 2021,42(9):1980-1984.
18	TOO C N, LI Y J, NJUKI S, et al.. A comparative study of fine-tuning deep learning models for plant disease identification [J]. Computers Electron. Agric., 2019,161:272-279.
19	黄双萍,孙超,齐龙,等.基于深度卷积神经网络的水稻穗瘟病检测方法[J]. 农业工程学报, 2017,33(20):169-176.
	HUANG S P, SUN C, QI L, et al.. Rice panicle blast identification method based on deep convolution neural network [J]. Trans. Chin. Soc. Agric. Eng., 2017,33(20):169-176.
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.
	LIU T Y, FENG Q, YANG S. Detecting grape diseases based on convolutional neural network [J]. J. Northeast Agric.Univ., 2018,49(3):73-83.
21	郭小清,范涛杰,舒欣. 基于改进Multi-Scale AlexNet的番茄叶部病害图像识别[J].农业工程学报, 2019,35(13):162-169.
	GUO X Q, FAN T J, SHU X. Tomato leaf diseases recognition based on improved multi-scale Alexnet [J]. Trans. Chin. Soc. Agric. Eng., 2019,35(13):162-169.
22	张敏,刘杰,蔡高勇.基于卷积神经网络的柑橘溃疡病识别方法[J].计算机应用, 2018,38(S1):48-52, 76.
	ZHANG M, LIU J, CAI G Y. Recognition method of citrus canker disease based on convolution neural network [J]. J. Computer Appl., 2018,38(S1):48-52, 76.
23	金瑛,叶飒,李洪磊.基于ResNet-50深度卷积网络的果树病害智能诊断模型研究[J].农业图书情报学报, 2021,33(4):58-67.
	JIN Y, YE S, LI H L. The intelligent diagnosis model of fruit tree disease based on ResNet-50 [J]. J. Library Inform. Sci. Agric., 2021,33(4):58-67.
24	宋晨勇,白皓然,孙伟浩,等.基于GoogLeNet改进模型的苹果叶病诊断系统设计[J].中国农机化学报, 2021,42(7):148-155.
	SONG C Y, BAI H R, SUN W H, et al.. Design of apple leaf disease diagnosis system based on GoogLeNet improved model [J]. J. Chin. Agric. Mechanization, 2021,42(7):148-155.
25	YAO N, NI F, WANG Z, et al.. L2 MXception: an improved Xception network for classification of peach diseases [J/OL]. Plant Methods, 2021,17: 36 [2022-04-12]. .
26	HUANG G, LIU Z, LAURENS V D M, et al. Densely connected convolutional networks [C]// IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recongnition. Honolulu, USA, 2016:2261-2269.
27	任胜男,孙钰,张海燕,等.基于one-shot学习的小样本植物病害识别[J].江苏农业学报, 2019,35(5):1061-1067.
	REN S N, SUN Y, ZHANG H Y, et al.. Plant disease identification for small sample based on one-shot learning [J]. Jiangsu J. Agric. Sci., 2019,35(5):1061-1067.
28	项小东,翟蔚,黄言态,等.基于Xception-CEMs神经网络的植物病害识别[J].中国农机化学报, 2021,42(8):177-186.
	XIANG X D, ZHAI W, HUANG Y T, et al.. Plant disease recognition based on Xception-CEMs neural network [J]. J. Chin. Agric. Mechanization, 2021,42(8):177-186.
29	宋余庆,谢熹,刘哲,等.基于多层EESP深度学习模型的农作物病虫害识别方法[J].农业机械学报, 2020,51(8):196-202.
	SONG Y Q, XIE X, LIU Z, et al.. Crop pests and diseases recognition method based on multi-level EESP model [J]. Trans. Chin. Soc. Agric. Machinery, 2020,51(8):196-202.
30	计雪伟,霍兴赢,薛端,等.基于深度学习的农作物病虫害识别方法[J].南方农机, 2020,51(23):182-183.
	JI X W, HUO X Y, XUE R, et al.. Identification of crop diseases and insect pests based on deep learning [J]. South Agric. Machinery, 2020,51(23):182-183.
31	敖良忠,马瑞阳,杨学文.基于DenseNet和ResNet融合的发动机孔探图像分类研究[J].计算技术与自动化, 2021,40(3):105-110, 183.
	AO L Z, MA R Y, YANG X W. Research on engine borescope images classification based on DenseNet and ResNet fusion [J]. Computing Technol. Autom., 2021,40(3):105-110, 183.

桃树病害类型 Type of peach tree disease	样本数 Number of samples	准确率 Accuracy rate/%
桃黑斑病 Peach black spot	569	98.28
桃褐腐病 Peach brown rot	336	94.12
桃黑星病 Peach scab	280	92.86
桃炭疽病 Peach anthracnose	282	96.55
桃缩叶病 Peach leaf curl	268	92.31
桃灰霉病 Peach botrytis cinerea	235	86.96
桃褐斑穿孔病 Peach brown spot perforation	208	85.00
桃霉斑穿孔病 Peach mildew and perforation	290	86.21
桃细菌性穿孔病 Peach bacterial perforation	283	85.71
桃树流胶病 Peach gummosis	268	92.31
桃树木腐病 Peach wood rot	244	95.83
负样本 Negative sample	1 000	98.00
总计 Total	4 263	93.65

桃树病害类型 Type of peach tree disease	样本数 Number of samples	准确率 Accuracy rate/%
桃黑斑病 Peach black spot	569	98.28
桃褐腐病 Peach brown rot	336	94.12
桃黑星病 Peach scab	280	92.86
桃炭疽病 Peach anthracnose	282	96.55
桃缩叶病 Peach leaf curl	268	92.31
桃灰霉病 Peach botrytis cinerea	235	86.96
桃褐斑穿孔病 Peach brown spot perforation	208	85.00
桃霉斑穿孔病 Peach mildew and perforation	290	86.21
桃细菌性穿孔病 Peach bacterial perforation	283	85.71
桃树流胶病 Peach gummosis	268	92.31
桃树木腐病 Peach wood rot	244	95.83
负样本 Negative sample	1 000	98.00
总计 Total	4 263	93.65

[1]	Yinyan GAO, Yi SUN, Baochun LI. Estimating of Wheat Ears Number in Field Based on RGB Images Using Unmanned Aerial Vehicle [J]. Journal of Agricultural Science and Technology, 2022, 24(3): 103-110.
[2]	ZHOU Huiru, WU Boming. Advances in Research on Deep Learning for Crop Disease Image Recognition [J]. Journal of Agricultural Science and Technology, 2021, 23(5): 61-68.
[3]	LYU Chunyang, LIU Shengping, GUO Xiuming, XIAO Shunfu, LIU Dazhong, YANG Feifei, LI Luhua. Detection of Honeybee Based on SSD Model [J]. Journal of Agricultural Science and Technology, 2021, 23(5): 98-107.
[4]	XU Beibei1, WANG Wensheng1,2*, GUO Leifeng1, CHEN Guipeng3. A Review and Future Prospects on Cattle Recognition Based on Non-contact Identification [J]. Journal of Agricultural Science and Technology, 2020, 22(7): 79-89.
[5]	DONG Wei1, QIAN Rong1, ZHANG Jie 2*, ZHANG Liping1, CHEN Hongbo2, ZHANG Meng1, ZHU Jingbo1, BU Yingqiao3. Vegetable Lepidopteran Pest Auto Recognition and Detection Counting Based on Deep Learning [J]. Journal of Agricultural Science and Technology, 2019, 21(12): 76-84.
[6]	SU Yi-feng§, DU Ke-ming§, LI Ying, SUN Zhong-fu*, ZHENG Fei-xiang. Preliminary Research on Diagnosis System Design of Wheat Diseases and Pests Based on the Internet of Things [J]. Journal of Agricultural Science and Technology, 2016, 18(2): 86-94.