基于卷积神经网络的农作物病害识别研究

doi:10.13304/j.nykjdb.2023.0785

中国农业科技导报 ›› 2025, Vol. 27 ›› Issue (4): 99-109.DOI: 10.13304/j.nykjdb.2023.0785

基于卷积神经网络的农作物病害识别研究

陈自立¹^,²(), 林卫¹(), 贺佳², 王来刚², 郑国清², 彭一龙¹^,², 焦家东¹, 郭燕²()

^1.河南师范大学计算机与信息工程学院，河南省教育人工智能与个性化学习重点实验室，河南新乡 453007
^2.河南省农业科学院农业经济与信息研究所，农业农村部黄淮海智慧农业技术重点实验室，郑州 450002

收稿日期:2023-10-26 接受日期:2024-02-06 出版日期:2025-04-15 发布日期:2025-04-15
通讯作者: 林卫,郭燕
作者简介:陈自立 E-mail： czl989898@163.com
基金资助:
国家自然科学基金项目(41601213);国家重点研发计划项目(2022YFD2001105);河南省重点研发与推广专项(232102111030);河南省农业科学院自主创新项目(2023ZC064)

Research Progress on Crop Diseases Identification Based on Convolutional Neural Network

Zili CHEN¹^,²(), Wei LIN¹(), Jia HE², Laigang WANG², Guoqing ZHENG², Yilong PENG¹^,², Jiadong JIAO¹, Yan GUO²()

^1.Henan Provincial Key Laboratory of Educational Artificial Intelligence and Personalized Learning，College of Computer and Information Engineering，Henan Normal University，Henan Xinxiang 453007，China
^2.Key Laboratory of Huang-Huai-Hai Smart Agricultural Technology of Ministry of Agriculture and Rural Affairs，Economy and Information，Henan Academy of Agricultural Sciences，Zhengzhou 450002，China

Received:2023-10-26 Accepted:2024-02-06 Online:2025-04-15 Published:2025-04-15
Contact: Wei LIN,Yan GUO

摘要/Abstract

摘要：

农作物病害对农业生产造成重大威胁，及时、准确的病害识别对制定防治措施和保证粮食安全具有重要意义。随着深度学习的迅猛发展，以卷积神经网络为代表的农作物病害识别方法越来越多地被采用。从基于不同数据集的病害识别、使用迁移学习与预训练的病害识别、病害识别模型的轻量化3个方面对卷积神经网络病害识别方法的优劣进行了比较，分析了现有方法存在的不足，并对未来发展趋势进行了展望，指出为实现农作物病害的自动检测，应构建更丰富数据集、结合多模态数据、进一步优化模型、使用机器人等设备。为减少粮食损失、实现精准农业管理、推动农业现代化和可持续发展提供重要的参考。

关键词: 深度学习, 卷积神经网络, 农作物病害, 识别

Abstract:

Crop diseases are major threats for agricultural production， so timely and accurate identification of disease is important for the development of control measures to ensure food security. With the rapid development of deep learning， convolutional neural networks are used more and more to identify crop diseases. This paper compared the advantages and disadvantages of convolutional neural network disease recognition methods from 3 aspects including disease recognition based on different data sets， disease recognition using transfer learning and pre-training， and lightweight of the disease recognition model. It also analyzed the shortcomings of the current methods and put forward the future development trend. It was pointed out that more abundant data sets should be constructed， multi-modal data should be combined， models should be further optimized， and robots should be used to implement automatic detection. It provided important references for reducing food loss， realizing precision agriculture management， promoting agricultural modernization and sustainable development.

Key words: deep learning, convolutional neural network, cropdiseases, identification

中图分类号:

S126

陈自立, 林卫, 贺佳, 王来刚, 郑国清, 彭一龙, 焦家东, 郭燕. 基于卷积神经网络的农作物病害识别研究[J]. 中国农业科技导报, 2025, 27(4): 99-109.

Zili CHEN, Wei LIN, Jia HE, Laigang WANG, Guoqing ZHENG, Yilong PENG, Jiadong JIAO, Yan GUO. Research Progress on Crop Diseases Identification Based on Convolutional Neural Network[J]. Journal of Agricultural Science and Technology, 2025, 27(4): 99-109.

图/表 4

参考文献 48

1	刘杰,曾娟,杨清坡,等.2023年农作物重大病虫害发生趋势预报[J].中国植保导刊,2023,43(1):32-35.
	LIU J, ZENG J, YANG Q P, et al.. Forecast of major crop diseases and pests in 2023 [J]. China Plant Prot., 2023,43(1):32-35.
2	DONG X Y, WANG Q, HUANG Q D, et al.. PDDD-PreTrain:a series of commonly used pre-trained models support image-based plant disease diagnosis [J/OL]. Plant Phenomics, 2023,5:0054 [2024-10-08]..
3	赵云娟,尹祥杰,屈丰年,等.“望闻问切” 四诊观察法在黄瓜病害诊断中的应用[J].农业开发与装备,2023(1):206-207.
4	杨怡华,王明郧,曹瑱艳,等.麦冬主要病害病原菌巢式多重PCR检测方法的建立[J].植物保护学报,2021,48(4):742-747.
	YANG Y H, WANG M Y, CAO T Y, et al.. Nested multiplex PCR to detect two major fungal pathogens of Mondo grass Ophiopogon japonicas [J]. J. Plant Prot., 2021,48(4):742-747.
5	傅华英,葛丹凤,李晓燕,等.甘蔗赤条病菌巢式PCR检测[J].植物保护学报,2017,44(2):276-282.
	FU H Y, GE D F, LI X Y, et al.. Nested-PCR detection of Acidovorax avenae subsp.avenae,the pathogen of red stripe on sugarcane [J]. J. Plant Prot., 2017,44(2):276-282.
6	AHMAD M, ABDULLAH M, MOON H, et al.. Plant disease detection in imbalanced datasets using efficient convolutional neural networks with stepwise transfer learning [J]. IEEE Access, 2021, 9:140565-140580.
7	HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006,313(5786):504-507.
8	SALEEM M H, POTGIETER J, ARIF K M. Automation in agriculture by machine and deep learning techniques:a review of recent developments [J]. Precis.Agric., 2021,22(6):2053-2091.
9	BHAKTA I, PHADIKAR S, MAJUMDER K, et al.. A novel plant disease prediction model based on thermal images using modified deep convolutional neural network [J]. Precis. Agric., 2023,24(1):23-39.
10	SETIAWAN W, ROCHMAN E M S, SATOTO B D, et al.. Machine learning and deep learning for maize leaf disease classification: a review [C]// Proceedigns of 5th International Conference on Electrical, Electronics, Informatics, and Vocational Education, Yogyakarta, Indonesia, 2022, 012-019.
11	WANG B B, ZHANG C X, LI Y Y, et al.. An ultra-lightweight efficient network for image-based plant disease and pest infection detection [J]. Precis. Agric., 2023, 24(5):1836-1861.
12	VAN DER KLIS R, ALANIZ S, MANCINI M, et al.. PDiscoNet: Semantically consistent part discovery for fine-grained recognition [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV), Paris, France, 2023, 1866-1876.
13	FANG T, CHEN P, ZHANG J, et al.. Crop leaf disease grade identification based on an improved convolutional neural network [J/OL]. J. Electron. Imaging, 2020, 29 (1):013004[2024-10-08]..
14	KAPOOR K, SINGH S, SINGH N P, et al.. Bell-pepper leaf bacterial spot detection using AlexNet and VGG-16 [C]// Proceedings of International Conference on Smart Computing and Communication, Singapore, 2023, 507-519.
15	CHEN Y P, WU Q F. Grape leaf disease identification with sparse data via generative adversarial networks and convolutional neural networks [J]. Precis. Agric., 2023,24(1):235-253.
16	CHEN Z, WU R, LIN Y, et al.. Plant disease recognition model based on improved YOLOv5 [J]. Agronomy, 2022, 12 (2): 365.
17	姜红花,杨祥海,丁睿柔,等.基于改进ResNet18的苹果叶部病害多分类算法研究[J].农业机械学报,2023,54(4):295-303.
	JIANG H H, YANG X H, DING R R, et al.. Identification of apple leaf diseases based on improved ResNet18 [J]. Trans. Chin. Soc. Agric. Mach., 2023,54(4):295-303.
18	孙艳歌,吴飞,姚建峰,等.多尺度自注意力特征融合的茶叶病害检测方法[J].农业机械学报,2023,54(12):308-315.
	SUN Y G, WU F, YAO J F, et al.. Tea disease detection method with multi-scale self-attention feature fusion[J]. Trans. Chin. Soc. Agric. Mach., 2023,54(12):308-315.
19	BHUGRA S, KAUSHIK V, GUPTA A, et al.. AnoLeaf: Unsupervised leaf disease segmentation via structurally robust generative inpainting [C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, Hawaii, 2023, 6415-6424.
20	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. Mach., 2020,51(8):196-202.
21	ZHU D J, TAN J B, WU C Y, et al.. Crop disease identification by fusing multiscale convolution and vision transformer [J/OL]. Sensors, 2023, 23(13):6015 [2024-10-08]. .
22	BANDI S R, VARADHARAJAN A, CHINNASAMY A. Performance evaluation of various statistical classifiers in detecting the diseased citrus leaves [J]. Int. J. Eng. Sci. Technol., 2013, 5 (2): 298-307.
23	SCHULER J P S, ROMANI S, ABDEL-NASSER M, et al.. Color-aware two-branch DCNN for efficient plant disease classification [J], MENDEL, 2022, 28 (1): 55-62.
24	KAYA Y, GÜRSOY E. A novel multi-head CNN design to identify plant diseases using the fusion of RGB images [J/OL] .Ecol. Inform., 2023,75:101998 [2024-10-08]. .
25	JASROTIA S, YADAV J, RAJPAL N, et al.. Convolutional neural network based maize plant disease identification [J]. Procedia Comput. Sci., 2023, 218(1): 1712-1721.
26	于明,李若曦,阎刚,等.基于颜色掩膜网络和自注意力机制的叶片病害识别方法[J].农业机械学报,2022,53(8):337-344.
	YU M, LI R X, YAN G, et al.. Crop diseases recognition method via fusion color mask and self-attention mechanism [J].Trans. Chin. Soc. Agric. Mach., 2022,53(8):337-344.
27	THAI H T, LE K H, NGUYEN N L T. FormerLeaf:an efficient vision transformer for cassava leaf disease detection [J/OL]. Comput. Electron. Agric., 2023,204:107518[2024-10-08]. .
28	李云红,张蕾涛,谢蓉蓉,等.基于AT-DenseNet网络的番茄叶片病害识别方法[J].江苏农业科学,2023,51(21):209-217.
	LI Y H, ZHANG L T, XIE R R, et al.. An identification method for tomato leaf disease based on AT-DenseNet network [J]. Jiangsu Agric. Sci., 2023, 51(21):209-217.
29	王瑞鹏,陈锋军,朱学岩,等.采用改进的EfficientNet识别苹果叶片病害[J].农业工程学报,2023,39(18):201-210.
	WANG R P, CHEN F J, ZHU X Y, et al.. Identifying apple leaf diseases using improved EfficientNet [J]. Trans. Chin. Soc. Agric. Eng., 2023, 39(18):201-210.
30	XIAO J R, CHUNG P C, WU H Y, et al.. Detection of strawberry diseases using a convolutional neural network [J/OL]. Plants, 2020,10(1):31 [2024-10-08]. .
31	李大湘,曾小通,刘颖.耦合全局与局部特征的苹果叶部病害识别模型[J].农业工程学报,2022,38(16):207-214.
	LI D X, ZENG X T, LIU Y. Apple leaf disease identification model by coupling global and patch features [J]. Trans. Chin. Soc. Agric. Eng., 2022, 38(16):207-214.
32	LI D, AHMED F, WU N, et al.. YOLO-JD:a deep learning network for jute diseases and pests detection from images [J/OL]. Plants (Basel), 2022, 11(7):937 [2024-10-08]. .
33	ALSHAMMARI H, GASMI K, BBEN LTAIFA I, et al.. Olive disease classification based on vision transformer and CNN models [J/OL]. Comput. Intell. Neurosci., 2022, 1:3998193[2024-10-08]. .
34	贾璐,叶中华.基于注意力机制和特征融合的葡萄病害识别模型[J].农业机械学报,2023,54(7):223-233.
	JIA L, YE Z H. Grape disease recognition model based on attention mechanism and feature fusion [J]. Trans. Chin. Soc. Agric. Mach., 2023, 54(7):223-233.
35	张楠楠,张晓,白铁成,等.基于CBAM-YOLO v7的自然环境下棉叶病虫害识别方法[J].农业机械学报, 2023, 54 (S1): 239-244.
	ZHANG N N, ZHANG X, BAI T C, et al.. Identification method of cotton leaf diseases and insect pests in natural environment based on CBAM-YOLO v7 [J]. Trans. Chin. Soc. Agric. Mach., 2023, 54 (S1): 239-244.
36	CHEN J, ZHANG D, NANEHKARAN Y A, et al.. Detection of rice plant diseases based on deep transfer learning [J]. J. Sci. Food Agric., 2020, 100(7):3246-3256.
37	李子茂,徐杰,郑禄,等.基于改进DenseNet的茶叶病害小样本识别方法[J].农业工程学报,2022,38(10):182-190.
	LI Z M, XU J, ZHENG L, et al.. Small sample recognition method of tea disease based on improved DenseNet [J]. Trans. Chin. Soc. Agric. Eng., 2022,38(10):182-190.
38	张文景,蒋泽中,秦立峰.基于弱监督下改进的CBAM-ResNet18模型识别苹果多种叶部病害[J].智慧农业(中英文), 2023, 5 (1): 111-121.
	ZHANG W J, JIANG Z Z, QIN L F. Identifying multiple apple leaf diseases based on the improved CBAM-ResNet18 model under weak supervision [J]. Smart Agric., 2023, 5 (1): 111-121.
39	周敏敏.基于迁移学习的苹果叶面病害Android检测系统研究[D].咸阳:西北农林科技大学, 2019.
	ZHOU M M. Apple foliage diseases recognition in android system with transfer learning-based [D]. Xianyang: Northwest A&F University, 2019.
40	SANIDA T, SIDERIS A, SANIDA M V, et al.. Tomato leaf disease identification via two-stage transfer learning approach [J/OL]. Smart Agric. Technol., 2023, 5:100275 [2024-10-08]. .
41	AYAZ M, SHAH S K, ULLAH K, et al.. Automatic early diagnosis of dome galls in Cordia dichotoma G. Forst. using deep transfer learning [J]. IEEE Access, 2023, 11: 59511-59523.
42	LI L J, DONG P J, WEI Z M, et al.. Automated knowledge distillation via Monte Carlo tree search [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023, 17413-17424.
43	FANG G, MA X, SONG M, et al.. Depgraph: towards any structural pruning [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023, 16091-16101.
44	邓朋飞,官铮,王宇阳,等.基于迁移学习和模型压缩的玉米病害识别方法[J].计算机科学, 2022, 49 (S2): 444-449.
	DENG P F, GUAN Z, WANG Y Y, et al.. Maize disease identification method based on transfer learning and model compression [J]. Comput. Sci., 2022, 49 (S2): 444-449.
45	王泽钧,马凤英,张瑜,等.基于注意力机制和多尺度轻量型网络的农作物病害识别[J].农业工程学报, 2022, 38 (S1): 176-183.
	WANG Z J, MA F Y, ZHANG Y, et al.. Crop disease identification based on attention mechanism and multi-scale lightweight network [J]. Trans. Chin. Soc. Agric. Eng., 2022, 38 (S1): 176-183.
46	彭玉寒,李书琴.基于重参数化MobileNetV2的农作物叶片病害识别模型[J].农业工程学报,2023,39(17):132-140.
	PENG Y H, LI S Q. Recognizing crop leaf diseases using reparameterized MobileNetV2 [J]. Trans. Chin. Soc. Agric. Eng., 2023, 39(17):132-140.
47	刘阳,高国琴.采用改进的SqueezeNet模型识别多类叶片病害[J].农业工程学报, 2021, 37 (2):187-195.
	LIU Y, GAO G Q. Identification of multi-class leaf diseases by using improved SqueezeNet model [J]. Trans. Chin. Soc. Agric. Eng., 2021, 37 (2):187-195.
48	JIA L, WANG T, CHEN Y, et al.. MobileNet-CA-YOLO: an improved YOLOv7 based on the MobileNetV3 and attention mechanism for rice pests and diseases detection [J/OL]. Agriculture, 2023, 13 (7):1285 [2024-10-08]. .

数据集 Data set	作物种类Crop type	图像种类 Image type	图像数量 Number of images	接网址 Wehsite
植物村 PlantVillage	14	38	54 303	https：//github.com/spMohanty/PlantVillage-Dataset
植物文档 PlantDoc	13	17	2 598	https：//github.com/pratikkayal/PlantDoc-Object-Detection-Dataset
水稻叶片病害数据集 Rice Leaf Disease Image Samples	1	4	5 932	https：//link.zhihu.com/？target=https%3A//data.mendeley.com/datasets/fwcj7stb8r/1
IP102	8	102	75 000	https：//github.com/xpwu95/IP102
DiaMOS	1	4	3 505	https：//zenodo.org/record/5557313
巴西阿拉比卡咖啡叶图像数据集 BRACOL	1	4	4 407	https：//data.mendeley.com/datasets/yy2k5y8mxg/1
木薯叶病数据集 Cassava Leaf Disease	1	5	21 397	https：//www.kaggle.com/competitions/cassava-leaf-disease-classification/data
植物病理学2020-FGVC7 Plant Pathology 2020-FGVC7	1	3	3 642	https：//www.kaggle.com/competitions/plant-pathology-2020-fgvc7/data
AI Challenger 2018病虫害分类数据集 AI Challenger 2018 Pest and disease classification data set	10	27	50 000	https：//aistudio.baidu.com/datasetdetail/76075
苹果叶部病理图像 Apple leaf pathology images	1	5	约20 000 About 20 000	https：//aistudio.baidu.com/datasetdetail/11591
小麦病害数据集 Large Wheat Disease Classification Dataset 2020	1	10	12 000（可获取4 500幅） 12 000（4 500 sheets are available）	https：//drive.google.com/drive/folders/1OHKtwD1UrdmhqxrpQEeF_X_pqKotxRGD

数据集 Data set	作物种类Crop type	图像种类 Image type	图像数量 Number of images	接网址 Wehsite
植物村 PlantVillage	14	38	54 303	https：//github.com/spMohanty/PlantVillage-Dataset
植物文档 PlantDoc	13	17	2 598	https：//github.com/pratikkayal/PlantDoc-Object-Detection-Dataset
水稻叶片病害数据集 Rice Leaf Disease Image Samples	1	4	5 932	https：//link.zhihu.com/？target=https%3A//data.mendeley.com/datasets/fwcj7stb8r/1
IP102	8	102	75 000	https：//github.com/xpwu95/IP102
DiaMOS	1	4	3 505	https：//zenodo.org/record/5557313
巴西阿拉比卡咖啡叶图像数据集 BRACOL	1	4	4 407	https：//data.mendeley.com/datasets/yy2k5y8mxg/1
木薯叶病数据集 Cassava Leaf Disease	1	5	21 397	https：//www.kaggle.com/competitions/cassava-leaf-disease-classification/data
植物病理学2020-FGVC7 Plant Pathology 2020-FGVC7	1	3	3 642	https：//www.kaggle.com/competitions/plant-pathology-2020-fgvc7/data
AI Challenger 2018病虫害分类数据集 AI Challenger 2018 Pest and disease classification data set	10	27	50 000	https：//aistudio.baidu.com/datasetdetail/76075
苹果叶部病理图像 Apple leaf pathology images	1	5	约20 000 About 20 000	https：//aistudio.baidu.com/datasetdetail/11591
小麦病害数据集 Large Wheat Disease Classification Dataset 2020	1	10	12 000（可获取4 500幅） 12 000（4 500 sheets are available）	https：//drive.google.com/drive/folders/1OHKtwD1UrdmhqxrpQEeF_X_pqKotxRGD

[1]	陈林涛, 刘兆祥, 蓝莹, 牟向伟, 马旭, 王日俊. 基于高光谱技术与主成分分析的稻种品种识别研究[J]. 中国农业科技导报, 2025, 27(3): 104-111.
[2]	邢卓冉, 丁松爽, 张凯, 马明, 郭文龙, 刘旭东, 时向东. 计算机视觉与深度学习技术在烟叶生产上的研究进展[J]. 中国农业科技导报, 2025, 27(1): 96-106.
[3]	胡国玉, 董娅兰, 古丽巴哈尔·托乎提, 刘广, 周建平. 基于机器视觉的葡萄藤结构分割方法研究[J]. 中国农业科技导报, 2024, 26(9): 105-111.
[4]	熊晓菲, 王秀琴, 庄翠珍, 郭家贤, 谢新锐, 吴建伟, 李奇峰. 基于ROI融合特征的柑橘炭疽病诊断方法[J]. 中国农业科技导报, 2024, 26(9): 83-92.
[5]	金慧萍, 牟海雯, 刘腾, 于佳琳, 金小俊. 基于深度卷积神经网络的青菜和杂草识别[J]. 中国农业科技导报, 2024, 26(8): 122-130.
[6]	李锐风, 杨云福, 杨永发, 于永顺. 基于机器视觉的玫瑰花检测与特征提取[J]. 中国农业科技导报, 2024, 26(4): 106-113.
[7]	李名博, 刘玉乐, 穆志民, 郭俊旺, 卫勇, 任东悦, 贾济深, 卫泽中, 栗宇红. 基于YOLOX-L-TN模型的番茄果实识别[J]. 中国农业科技导报, 2024, 26(4): 97-105.
[8]	张晓卫, 陈波, 王月明, 李子剑, 张继红, 曹天一. 基于多角度数据融合的养殖场通道中奶牛身份识别算法研究[J]. 中国农业科技导报, 2024, 26(12): 98-106.
[9]	朱芷芫, 王海峰, 李斌, 赵文文, 朱君, 贾楠, 赵宇亮. 深度学习在畜禽典型行为识别中的研究进展[J]. 中国农业科技导报, 2024, 26(10): 110-124.
[10]	郑果, 姜玉松. 基于多任务学习农作物叶片病害诊断方法[J]. 中国农业科技导报, 2024, 26(1): 89-98.
[11]	钱政, 杨孙哲, 张国卿, 郭紫微, 张林朋, 万家兴, 杨红云. 基于卷积神经网络的水稻氮素营养诊断[J]. 中国农业科技导报, 2023, 25(9): 113-121.
[12]	赵宁, 李星, 江勇, 王志秀, 毕瑜林, 陈国宏, 白皓, 常国斌. 图像识别技术在鸡养殖领域的应用[J]. 中国农业科技导报, 2023, 25(9): 13-22.
[13]	林开颜, 梅飞, 吴军辉, 郭文刚, 陈杰, 司慧萍. 基于计算机视觉的作物病害监测服务平台设计与研究[J]. 中国农业科技导报, 2023, 25(6): 89-96.
[14]	赵威, 马睿, 王佳, 郭宏杰, 许金普. 基于果穗图像的玉米品种分类识别[J]. 中国农业科技导报, 2023, 25(6): 97-106.
[15]	刘朝阳, 王永强, 周聪玲, 强斯祺. 室外池塘养殖投饵系统智能控制方法研究[J]. 中国农业科技导报, 2023, 25(5): 123-130.

基于卷积神经网络的农作物病害识别研究

Research Progress on Crop Diseases Identification Based on Convolutional Neural Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 48

相关文章 15

编辑推荐

Metrics