| 808 | 1 | 432 |
| 下载次数 | 被引频次 | 阅读次数 |
综述了从机器学习到卷积神经网络（convolutional neural network, CNN）的作物病害识别融合改进方法，系统梳理了机器学习与CNN作物病害识别的关键技术，包括数据获取、数据处理、数据训练、网络架构选择、特征提取与融合、模型验证等6个应用流程，分析了两者性能差异的核心原因，归纳了二者共同面临的数据需求高、计算资源高和泛化能力不足的技术难点，对应总结了机器学习改进卷积神经网络作物病害识别关键技术的策略。最后，总结了当前研究存在的挑战，并展望了未来的研究方向。
Abstract：This review summarizes the integrated improvement methods for crop disease identification, evolving from machine learning to convolutional neural network(CNN). It systematically outlines the key technologies involved in both machine learning and CNN-based crop disease indentification, including six major application processes: data acquisition, data preprocessing, model training, network architecture selection, feature extraction and fusion, and model validation. The core reasons for the performance differences between the two methods are analyzed, and the shared technical challenges(such as high data requirements, high computational demands, and limited generalization capability) are identified. Corresponding strategies for using machine learning to enhance CNN-based crop disease identification are also summarized. Finally, the review highlights current research challenges and discusses potential future research directions.
[1]李佳盟，王楠，李震，等.基于特征波长优化的便携式作物叶绿素检测仪研究[J].农业机械学报，2023,54（增刊2）:270-277.LI J M, WANG N, LI Z, et al. Development of handheld chlorophyll detector based on characteristic wavelengths optimization[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(Suppl2):270-277.
[2]尚俊平，张冬阳，席磊，等.基于多尺度特征融合和注意力机制的辣椒病害识别模型[J].河南农业大学学报，2024, 58(6):1021-1033.SHANG J P, ZHANG D Y, XI L, et al. Pepper disease identification model based on multi-scale feature fusion and attention mechanism[J]. Journal of Henan Agricultural University, 2024, 58(6):1021-1033.
[3]李子涵，周省邦，赵戈，等.基于卷积神经网络的农业病虫害识别研究综述[J].江苏农业科学，2023,51(7):15-23.LI Z H, ZHOU S B, ZHAO G, et al. Study on agricultural pest identification based on convolutional neural network:a review[J]. Jiangsu Agricultural Sciences,2023, 51(7):15-23.
[4]张耀丽，许宁，宋裕民，等.卷积神经网络在农业病虫害识别中的应用[J].农业装备与车辆工程，2023,61(2):58-62.ZHANG Y L, XU N, SONG Y M, et al. Application of convolution neural network in pest identification[J].Agricultural Equipment&Vehicle Engineering, 2023,61(2):58-62.
[5]刘峻渟，周云成，吴琼，等.基于卷积神经网络的番茄叶部病害识别方法[J].河南农业大学学报，2024,58(2):287-297.LIU J T, ZHOU Y C, WU Q, et al. Recognition method of tomato leaf diseases based on convolutional neural network[J]. Journal of Henan Agricultural University, 2024, 58(2):287-297.
[6]王美娟，尹飞.卷积神经网络的多尺度改进及其在玉米病害症状识别中的应用[J].河南农业大学学报，2021, 55(5):906-916.WANG M J, YIN F. Multi-scale improvement of convolutional neural network and its application in symptom recognition of maize disease[J]. Journal of Henan Agricultural University, 2021, 55(5):906-916.
[7]刘媛媛，张凡，师琪，等.基于高光谱和集成学习的库尔勒香梨黑斑病潜育期诊断[J].农业机械学报，2022, 53(6):295-303.LIU Y Y, ZHANG F, SHI Q, et al. Diagnosis of Korla pear black spot disease in incubation period based on hyperspectral imaging and ensemble learning algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(6):295-303.
[8] SINGH A K, SREENIVASU S, MAHALAXMI U S B K, et al. Hybrid feature-based disease detection in plant leaf using convolutional neural network, Bayesian optimized SVM, and random forest classifier[J]. Journal of Food Quality, 2022, 2022:2845320.
[9] ZHAO X, LI K Y, LI Y X, et al. Identification method of vegetable diseases based on transfer learning and attention mechanism[J]. Computers and Electronics in Agriculture, 2022, 193:106703.
[10]杨振东，骆巍，罗晨，等.黄瓜病害智能识别技术研究进展[J].河南农业科学，2025, 54(4):1-10.YANG Z D, LUO W, LUO C, et al. Research progress on intelligent identification technology of cucumber diseases[J]. Journal of Henan Agricultural Sciences,2025, 54(4):1-10.
[11]彭宇龙，孙小芳，黄云，等.纳米ZnO在植物病害防控中的应用研究进展[J].河南农业科学，2025, 54(2):1-9.PENG Y L, SUN X F, HUANG Y, et al. Research progress on nano-ZnO applications in plant disease control[J]. Journal of Henan Agricultural Sciences, 2025,54(2):1-9.
[12]肖天赐，陈燕红，李永可，等.基于改进通道注意力机制的农作物病害识别模型研究[J].江苏农业科学，2023, 51(24):168-175.XIAO T C, CHEN Y H, LI Y K, et al. Study on crop disease identification model based on improved channel attention mechanism[J]. Jiangsu Agricultural Sciences, 2023, 51(24):168-175.
[13] RAHMANI M K I, GHANIMI H M A, JILANI S F, et al. Early pathogen prediction in crops using nano biosensors and neural network-based feature extraction and classification[J]. Big Data Research, 2023, 34:100412.
[14]李艳玲，张博翔，董萍，等.基于改进DCGAN的小样本玉米病害图像扩充方法[J/OL].河南农业大学学报，2024:1-16(2024-09-25). https：//link. cnki.net/doi/10. 16445/j. cnki. 1000-2340. 20240925. 001.LI Y L, ZHANG B X, DONG P, et al. Few-Shot corn disease image augmentation method based on improved DCGAN[J/OL]. Journal of Henan Agricultural University, 2024:1-16(2024-09-25). https：//link. cnki. net/doi/10. 16445/j. cnki. 1000-2340. 20240925. 001.
[15] HE P D, LI X J, SHEN W Q, et al. Traceability and analysis method for measurement laboratory testing data based on intelligent Internet of Things and deep belief network[J]. Journal of Intelligent Systems, 2024, 33:20240076.
[16] JIANG P, CHEN Y H, LIU B, et al. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks[J].IEEE Access, 2019, 7:59069-59080.
[17] SINGH R, KRISHNAN P, BHARADWAJ C, et al.Improving prediction of chickpea wilt severity using machine learning coupled with model combination techniques under field conditions[J]. Ecological Informatics, 2023, 73:101933.
[18] AHILA PRIYADHARSHINI R, ARIVAZHAGAN S,ARUN M, et al. Maize leaf disease classification using deep convolutional neural networks[J]. Neural Computing and Applications, 2019, 31(12):8887-8895.
[19] SALEEM M H, POTGIETER J, ARIF K M. Plant disease classification:a comparative evaluation of convolutional neural networks and deep learning optimizers[J]. Plants, 2020, 9(10):1319.
[20] ARSENOVIC M, KARANOVIC M, SLADOJEVIC S,et al. Solving current limitations of deep learning based approaches for plant disease detection[J]. Symmetry,2019, 11(7):939.
[21] TAO J X, LI X L, HE Y, et al. CEFW-YOLO:a highprecision model for plant leaf disease detection in natural environments[J]. Agriculture, 2025, 15(8):833.
[22] VALLABHAJOSYULA S, SISTLA V, KOLLI V K K.Transfer learning-based deep ensemble neural network for plant leaf disease detection[J]. Journal of Plant Diseases and Protection, 2022, 129(3):545-558.
[23] GAO C F, JI X J, HE Q, et al. Monitoring of wheat Fusarium head blight on spectral and textural analysis of UAV multispectral imagery[J]. Agriculture, 2023, 13(2):293.
[24]李慧琴，宋赵铭，刘存祥，等.基于YOLOv8n的番茄果实检测模型改进[J/OL].河南农业大学学报，2024:1-14(2024-05-13). https：//link. cnki. net/doi/10. 16445/j. cnki. 1000-2340. 20240511. 002.LI H Q, SONG Z M, LIU C X, et al. Improvement of tomato fruit detection model based on YOLOv8n[J/OL].Journal of Henan Agricultural University, 2024:1-14(2024-05-13). https：//link. cnki. net/doi/10. 16445/j.cnki. 1000-2340. 20240511. 002.
[25]黄河清，胡嘉沛，李震，等.基于模型剪枝改进FCOS的实时柑橘检测研究[J].河南农业大学学报，2021,55(3):453-459.HUANG H Q, HU J P, LI Z, et al. Real time Citrus detection research based on improved FCOS with model pruning[J]. Journal of Henan Agricultural University,2021, 55(3):453-459.
[26]刘佳明，张欣，陈孝玉龙，等.基于改进MobileNetV2的番茄病害识别研究[J].南京农业大学学报，2025,48(3):724-733.LIU J M, ZHANG X, CHEN X, et al. A study on tomato disease recognition based on improved MobileNetV2[J]. Journal of Nanjing Agricultural University,2025, 48(3):724-733.
[27]张红涛，罗一铭，谭联，等.基于迁移学习和残差网络的谷子病害识别研究[J].河南农业科学，2023,52(12):162-171.ZHANG H T, LUO Y M, TAN L, et al. Research on millet disease identification based on transfer learning and residual network[J]. Journal of Henan Agricultural Sciences, 2023, 52(12):162-171.
[28]李伟豪，詹炜，周婉，等.轻量型Yolov7-TSA网络在茶叶病害检测识别中的研究与应用[J].河南农业科学，2023, 52(5):162-169.LI W H, ZHAN W, ZHOU W, et al. Research and application of lightweight Yolov7-TSA network in tea disease detection and identification[J]. Journal of Henan Agricultural Sciences, 2023, 52(5):162-169.
[29] COULIBALY S, KAMSU-FOGUEM B, KAMISSOKO D, et al. Deep neural networks with transfer learning in millet crop images[J]. Computers in Industry, 2019,108:115-120.
[30] AL-GAASHANI M S A M, SHANG F J, ABD ELLATIF A A. Ensemble learning of lightweight deep convolutional neural networks for crop disease image detection[J]. Journal of Circuits, Systems and Computers,2023, 32(5):2350086.
[31] RAJ N, PERUMAL S, SINGLA S, et al. Computer aided agriculture development for crop disease detection by segmentation and classification using deep learning architectures[J]. Computers and Electrical Engineering, 2022, 103:108357.
[32] WAN S, YEH M L, MA H L. An innovative intelligent system with integrated CNN and SVM:considering various crops through hyperspectral image data[J]. ISPRS International Journal of Geo-Information, 2021, 10(4):242.
[33] WANG Y M, ZHANG Z, FENG L W, et al. A new attention-based CNN approach for crop mapping using time series Sentinel-2 images[J]. Computers and Electronics in Agriculture, 2021, 184:106090.
[34]何前，郭峰林，方皓正，等.基于改进LeNet-5模型的玉米病害识别[J].江苏农业科学，2022, 50(20):35-41.HE Q, GUO F L, FANG H Z, et al. Study on maize disease recognition based on improved LeNet-5 model[J].Jiangsu Agricultural Sciences, 2022, 50(20):35-41.
[35]韩鑫，徐衍向，封润泽，等.基于红外热成像和改进YOLO v5的作物病害早期识别[J].农业机械学报，2023, 54(12):300-307.HAN X, XU Y X, FENG R Z, et al. Early identification of crop diseases based on infrared thermography and improved YOLO v5[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(12):300-307.
[36]杨英茹，吴华瑞，张燕，等.基于复杂环境的番茄叶部图像病虫害识别[J].中国农机化学报，2021, 42(9):177-186.YANG Y R, WU H R, ZHANG Y, et al. Tomato disease recognition using leaf image based on complex environment[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(9):177-186.
[37]廖露，韩春峰，何纯樱.基于VGG19卷积神经网络和迁移学习的水稻病害图像分类方法[J].测绘，2023, 46(4):153-157.LIAO L, HAN C F, HE C Y. Rice diseases image classification method based on VGG19 and transfer learning[J]. Surveying and Mapping, 2023, 46(4):153-157.
[38]张娜，刘坤，杨国栋.基于AlexNet的农作物病虫害识别研究[J].计算机与数字工程，2024, 52(2):554-558.ZHANG N, LIU K, YANG G D. Research on crop pest and disease identification based on AlexNet[J]. Computer&Digital Engineering, 2024, 52(2):554-558.
[39]何前.基于卷积神经网络的水稻叶片病害分类研究[D].武汉：武汉轻工大学，2023.HE Q. Classification of rice leaf diseases based on convolutional neural network[D]. Wuhan:Wuhan Polytechnic University, 2023.
[40]尚增强，杨东福，马质璞.基于深度卷积神经网络的大豆叶片多种病害分类识别[J].大豆科学，2021,40(5):662-668.SHANG Z Q, YANG D F, MA Z P. Automatic identification of soybean leaf diseases based on UAV image and deep convolution neural network[J]. Soybean Science,2021, 40(5):662-668.
[41]赵小虎，李晓，叶圣，等.基于改进U-Net网络的多尺度番茄病害分割算法[J].计算机工程与应用，2022, 58(10):216-223.ZHAO X H, LI X, YE S, et al. Multi-scale tomato disease segmentation algorithm based on improved U-Net network[J]. Computer Engineering and Applications,2022, 58(10):216-223.
[42]吴秀庆，李彩斌，罗杰，等.贵州烟草根结线虫种类鉴定及其与根茎类病害混合侵染情况调查[J].南方农业学报，2024, 55(10):3013-3022.WU X Q, LI C B, LUO J, et al. Identification of tobacco root-knot nematode species and survey on their mixed infestations with root and Tuber diseases in Guizhou[J]. Journal of Southern Agriculture, 2024, 55(10):3013-3022.
[43]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.ZHENG G, JIANG Y S. Diagnosis of crop disease based on multi-task learning[J]. Journal of Agricultural Science and Technology, 2024, 26(1):89-98.
[44]蒋权，罗明涛，黄梓琛，等.基于空地多视角RGB影像协同的病害香蕉植株监测[J].南方农业学报，2023, 54(10):3114-3124.JIANG Q, LUO M T, HUANG Z C, et al. Monitoring of diseased banana plants based on collaborative RGB images from air-ground multi-view[J]. Journal of Southern Agriculture, 2023, 54(10):3114-3124.
[45]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]. Journal of Agricultural Science and Technology, 2021, 23(5):61-68.
[46]李长明，张勇，刘志勇.局部线性与卷积网络融合的病害图像分割算法[J].计算机仿真，2020, 37(7):418-421.LI C M, ZHANG Y, LIU Z Y. A disease image segmentation algorithm based on the fusion of local linear and convolutional networks[J]. Computer Simulation,2020, 37(7):418-421.
[47] REZK N G, ATTIA A F, EL-RASHIDY M A, et al. An efficient plant disease recognition system using hybrid convolutional neural networks(CNNs)and conditional random fields(CRFs)for smart IoT applications in agriculture[J]. International Journal of Computational Intelligence Systems, 2022, 15(1):65.
[48] ZHONG Y W, HUANG B J, TANG C W. Classification of cassava leaf disease based on a non-balanced dataset using transformer-embedded ResNet[J]. Agriculture,2022, 12(9):1360.
[49]王浩宇，胡玉荣，崔艳荣，等.基于改进MobileNet v3-small模型的苹果叶片病害识别方法[J].江苏农业科学，2025, 53(5):113-120.WANG H Y, HU Y R, CUI Y R, et al. Apple leaf disease identification method based on improved MobileNet v3-small model[J]. Jiangsu Agricultural Sciences, 2025, 53(5):113-120.
[50]卢筱伟，孟志青.融合注意力机制和多尺度卷积的小麦病害识别模型[J].中国农学通报，2023, 39(25):147-154.LU X W, MENG Z Q. Wheat disease recognition model integrating attention mechanism and multi-scale convolution[J]. Chinese Agricultural Science Bulletin, 2023,39(25):147-154.
[51]崔庭源，杨其长，张义，等.基于迁移学习和卷积神经网络的生菜鲜重估测[J].中国农业大学学报，2022, 27(11):197-206.CUI T Y, YANG Q C, ZHANG Y, et al. Lettuce fresh weight estimation based on transfer learning and convolutional neural network[J]. Journal of China Agricultural University, 2022, 27(11):197-206.
[52]樊湘鹏，许燕，周建平，等.基于迁移学习和改进CNN的葡萄叶部病害检测系统[J].农业工程学报，2021, 37(6):151-159.FAN X P, XU Y, ZHOU J P, et al. Detection system for grape leaf diseases based on transfer learning and updated CNN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(6):151-159.
[53] MALLICK M T, MURTY D O, PAL R, et al. Highspeed system-on-chip-based platform for real-time crop disease and pest detection using deep learning techniques[J]. Computers and Electrical Engineering,2025, 123:110182.
[54] PANDIYARAJU V, ANUSHA B, SENTHIL KUMAR A M, et al. Spatial attention-based hybrid VGG-SVM and VGG-RF frameworks for improved cotton leaf disease detection[J]. Neural Computing and Applications,2025, 37(14):8309-8329.
[55]罗鸣，方睿，徐铭美，等.基于迁移学习和轻量级卷积神经网络农作物病害识别[J].现代计算机，2021,27(32):16-21.LUO M, FANG R, XU M M, et al. Agricultural crop disease identification based on transfer learning and lightweight convolution neural network[J]. Modern Computer, 2021, 27(32):16-21.
[56] THAKUR P S, SHEOREY T, OJHA A. VGG-ICNN:a lightweight CNN model for crop disease identification[J]. Multimedia Tools and Applications, 2023, 82(1):497-520.
[57] WU C H, GU X X, XIONG H L, et al. Fine-grained recognition of grape leaf diseases based on transfer learning and convolutional block attention module[J].Applied Soft Computing, 2025, 172:112896.
[58]张会敏，谢泽奇.基于多尺度注意力卷积神经网络的苹果叶部病害识别方法[J].江苏农业科学，2023,51(16):154-161.ZHANG H M, XIE Z Q. An apple leaf disease identification method based on multi-scale attention convolution neural network[J]. Jiangsu Agricultural Sciences,2023, 51(16):154-161.
[59]张净，邵文文，刘晓梅，等.基于超图的双模态特征融合的作物病害识别算法[J].江苏农业科学，2023,51(15):164-173.ZHANG J, SHAO W W, LIU X M, et al. Crop disease identification based on bimodal feature fusion and HGNN[J]. Jiangsu Agricultural Sciences, 2023, 51(15):164-173.
[60] FENG S, ZHAO D X, GUAN Q, et al. A deep convolutional neural network-based wavelength selection method for spectral characteristics of rice blast disease[J]. Computers and Electronics in Agriculture, 2022,199:107199.
[61] CHENG H B, LI H M. Identification of apple leaf disease via novel attention mechanism based convolutional neural network[J]. Frontiers in Plant Science, 2023,14:1274231.
基本信息:
DOI：10.16445/j.cnki.1000-2340.20250828.001
中图分类号:TP183;TP391.41;S432
引用信息:
[1]汪强,李美琳,马新明,等.机器学习改进卷积神经网络在作物病害识别中的研究进展[J].河南农业大学学报,2025,59(05):767-775.DOI:10.16445/j.cnki.1000-2340.20250828.001.
基金信息:
“十四五”国家重点研发计划（2023YFD2301503）; 国家自然科学基金项目（32271993）; 河南省科技研发计划联合基金优势学科培育项目（222301420114）; 河南省科技攻关国际科技合作项目（242102521027）