农作物病虫害图像识别技术的研究综述

摘要/Abstract

摘要：

农作物病虫害的爆发往往意味着大规模的减产减质，造成不可挽回的经济损失。传统的病虫害识别方法速度慢、主观性强、误判率高，已不能满足农业生产的需要。基于图像处理技术的农作物病虫害识别具有快速、精确、实时等特点，能够协助农耕人员及时采取有效的防治措施。本文从图像分割、特征值提取和分类识别三个方面，分别阐述图像处理技术应用于农作物病虫害识别的研究现状和进展，并对今后的研究趋势和方向作了展望。

关键词: 图像处理, 病虫害, 图像分割, 特征提取, 分类识别

Abstract:

The outbreak of crop pests and diseases often means large scales of production and quality decline which can lead to irrecoverable economic losses. The traditional disease and pest identification approach is slow, subjective and not accurate, not suitable for the current agricultural production. The image processing based crop disease and pest identification is fast, accurate and realtime, and it can assist farmers to timely adopt effective preventative methods. This thesis describes the study status and progress of image processing technology’s application on crop disease and pest identification in image segmentation, feature extraction and classification, and outlooks into the future trend and direction of further studies.

Key words: image processing;diseases and pests;segmentation;feature extraction;classification and recognition

汪京京1，张武1,2，刘连忠1，黄帅1. 农作物病虫害图像识别技术的研究综述[J]. J4, 2014, 36(07): 1363-1370.

WANG Jingjing1,ZHANG Wu1,2,LIU Lianzhong1,HUANG Shuai1. Summary of crop diseases and
pests image recognition technology [J]. J4, 2014, 36(07): 1363-1370.

参考文献

［1］Lucas B G, Campbell C L, Lucas L T. Introduction to plant diseases:Identification and management ［M］. US:Van Nostrand Reinhold, 1992.
［2］Han Siqi, Wang Lei. A survey of thresholding methods for image segmentation［J］. Systems Engineering and Electronics,2002,24(6):9194.(in Chinese)
［3］Xinxiong S.In accordance with the image extracting plant growth information［Z］. The 6th Branch Research Data of the Agricultural Society of Mechanical Engineers, 1989:12.(in Chinese)
［4］Chen Jiajuan,Zhao Xuedu.Automatic measurement of danger degree of cotton insect pests using computer vision［J］. Transactions of the Chinese Society of Agricultural Engineering, 2001, 17(2):157160.(in Chinese)
［5］Camargo A, Smith J S. An imageprocessing based algorithm to automatically identify plant disease visual systems［J］. Biosystems Engineering,2009(102):921.
［6］Duan Ruiling, Li Qingxiang, Li Yuhe. Summary of image edge detection［J］.Optical Technique,2005,31（3）:415419.(in Chinese)
［7］Baum T,Seiffert U. Hyph areaautomated analysis of spatiotemporal fungal patterns［J］.Journal of Plant Physiology,2011(68):7278．
［8］He Dandan,Xu Mei.Rice leaf edge detection algorithm based on multistrategy fusion technique［J］. Journal of Northeast Agricultural University,2012,43(5):6568.(in Chinese)
［9］Nalwa V S,Binford T O.On detecting edges［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):699714.
［10］Casady W W, Singh N, Costello T A. Machine vision for measurement of rice canopy dimensions ［J］.Transactions of the ASAE, 1996, 39(5):18911898.
［11］Wang Ping,Tang Jiangfeng,Wang Bo, et al. Image segmentation method of plant leaves based on mathematical morphology［J］. Acta Agriculturae Zhejiangensis, 2012,24(3):509513.(in Chinese)
［12］Ren Lei,Lai Huicheng,Chen Qinzheng, et al. Cotton image segmentation method based on improved watershed［J］. Computer Engineering and Applications,2012,48（34）:207212.(in Chinese)
［13］Sun Jigui, Liu Jie, Zhao Lianyu. Clustering algorithms research［J］. Journal of Software,2008,19(1):4861.(in Chinese)
［14］Wang Shouzhi, He Dongjian,Li Wen, et al. Plant leaf disease recognition based on kernel Kmeans clustering algorithm［J］. Transactions of the Chinese Society for Agricultural Machinery,2009, 40（3）:152155.(in Chinese)
［15］Jaware T H, Badgujar R D, et al. Crop disease detection using image segmentation ［J］. World Journal of Science and Technology, 2012,2(4):190194.
［16］Ostu N.A threshold selection method from gray level histogram［J］.IEEE Transactions on SMC,1979(9):652655.
［17］Li Zhen,Hong Tiansheng,Zeng Xiangye, et al. Citrus red mite image target identification based on Kmeans clustering［J］. Transactions of the Chinese Society of Agricultural Engineering,2012,28（23）:147153.(in Chinese)
［18］Diao Zhihua,Song Yinmao,Wang Huan, et al. Study surveys on image segmentation of plant disease spot［J］. Journal of Agricultural Mechanization Research,2012, 10(10):111.(in Chinese)
［19］Lai Junchen,Tang Xiujuan,Li Shaokun,et al.Maize leaf disease spots segmentation based on GaussMRF model［J］. Scientia Agricultura Sinica, 2010, 43(7):13631369.(in Chinese)
［20］Yuan Yuan,Li Miao,Liang Qing,et al.Segmentation method for crop disease leaf images with complex background［J］. Transactions of the Chinese Society of Agricultural Engineering,2011,27(2):208212.(in Chinese)
［21］Hu Xiaohong,Li Bingjun,Xi Lei. Multiinstance graph approach to wheat leaf disease segmentation［J］. Transactions of the Chinese Society of Agricultural Engineering,2012,28(13):154159.(in Chinese)
［22］Woebbecke D M,Meyer G E，Bargen KV, et al. Shape features for identifying young weeds using image analysis［J］.Transactions of the ASAE, 1995,38(1):271281.
［23］Chesmore D, Bernard T, Inman A J, et al. Image analysis for the identification of the quarantine pest Tilletia Indica ［J］.EPPO Bulletin,2003,3（3）:495499.
［24］Zhang Hongtao,Mao Hanping,Qiu Daoyin. Feature extraction for the storedgrain insect detection system based on image recognition technology［J］. Transactions of the Chinese Society of Agricultural Engineering, 2009, 25(2):126130.(in Chinese)
［25］Diao Zhihua,Zheng Anping,Wu Yuanyuan.Shape feature extraction of wheat leaf disease based on invariant moment theory［J］.IFIP Advances in Information and Communication Technology, 2012（369）:168173.
［26］Xu Guili, Mao Hanping, Li Pingping. Extracting color features of leaf color images［J］. Transactions of the Chinese Society of Agricultural Engineering,2002,18（4）:150154.(in Chinese)
［27］Jafari A,Mohtasebi S S,Jahromi H E, et al. Color feature extraction by means of discriminant analysis for weed segmentation［J］. The Canadian Society for Engineering in Agricultural,Food,and Biological Systems,2004.
［28］Zhu Hong, Zheng Limin, Yin Jianling, et al. Nitrogen evaluation of winter wheat based on color features of canopy images［J］. Transactions of the Chinese Society of Agricultural Engineering,2010, 26(2):1620.(in Chinese)
［29］Tuceryan M, Jain A K. Texture analysis, Handbook pattern recognition and computer vision［M］. Singapore :World Scientific,1993.
［30］Xu Guili, Mao Hanping Li Pingping. Research on extraction leaf texture features as sample of nutrient shortage by percent histogram of differentiation［J］. Transactions of the Chinese Society of Agricultural Machinery,2003,34(2):7679.(in Chinese)
［31］Pydipati R, Burks T F, et al. Identification of citrus disease using color texture features and discriminant analysis［J］. Computers and Electronics in Agriculture,2006(52):4959.
［32］Gu Qingkui. A pattern recognition system about maize leaf disease based on computer image processing［D］.Shenyang:Shenyang Ligong University,2008.(in Chinese)
［33］Liu li,Kuang Gangyao. Overview of image textural feature extraction methods［J］. Journal of Image and Graphics, 2009,14(4):622635.(in Chinese)
［34］Mao Hanping, Xu Guili, Li Pingping. Extracting and selecting features of leaf images for diagnosing nutrient deficiency diseases in tomatoes［J］. Transactions of the Chinese Society of Agricultural Engineering, 2003, 19(2):1.(in Chinese)
［35］Liang Jiaxi. The research and application on cucumber scle rophthora macrospora experimental based on the image processing［D］.Changchun:Jilin University, 2011.(in Chinese)
［36］Patil J K, Raj K. Feature extraction of diseased leaf images ［J］. Journal of Signal and Image Processing，2012, 3(1)：6063.
［37］Wang Liya. Feature extraction and classification for images［D］.Xi’an:Xidian University,2006.(in Chinese)
［38］Shanwen H.Image processing technology in environmental applications［M］∥Electric Association Journal Featured, 1985:455458.(in Chinese)
［39］Zayas I Y,Inna Y.Detection of insects in bulks wheat samples with machine vision［J］.Transaction of the ASAE,1986,6(3):883888.
［40］Sasaki Y， Okamoto T. Automatic diagnosis of plant disease recognition between healthy and healthy and diseased leaf ［J］. Journal of JSAM,1999,61(2)：119126.
［41］Gassoumi H, Prasad N R, Ellington J J. Neural networkbased approach for insect classification in cotton ecosystems［C］∥Proc of International Conference on Intelligent Technologies, 2007:1.
［42］Qi Guangyun,Ma Xiaodan,Guan Haiou. Extraction of the image of soybean target leaf spot based on improved genetic algorithm［J］. Transactions of the Chinese Society of Agricultural Engineering,2009, 25(5):142145.(in Chinese)
［43］Wen Zhiyuan,Cao Leping. Image recognition of navel orange diseases and insect pests based on compensatory fuzzy neural networks［J］. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28 (11):152157.(in Chinese)
［44］Zhang Xuegong. Intronduction to statistical learning theory and support vector machines［J］. Acta Automatica Sinica,2000,26(1):3242.(in Chinese)
［45］Tian Youwen, Zhang Changshui, Li Chenghua. Application of support vector machine to shape recognition of plant disease spot［J］. Transactions of the Chinese Society of Agricultural Engineering, 2004,20(3):134136.(in Chinese)
［46］Tian Youwen,Niu Yan. Applied research of support vector machine on recognition of cucumber disease［J］. Journal of Agricultural Mechanization Research,2009(3):3639.(in Chinese)
［47］Diao Zhihua. Research and application of intelligent system of field wheat leaf disease detection［D］.Hefei:University of Science and Technology of China,2010.(in Chinese)
［48］Zhang Jianhua,Ji Ronghua,Yuan Xue, et al. Recognition of pest damage for cotton leaf based on RBFSVM algorithm［J］. Transactions of the Chinese Society for Agricultural Machinery, 2011,42(8):178183.(in Chinese)
［49］Du Ruiqing,Zhang Zhengtian,Liu Guangliang,et al.Application of roughset theory and fuzzy clustering analysis in insect taxonomy［J］. Acta Entomologica Sinica,2006, 49(1):106111.(in Chinese)
［50］Zhao Jinhui , Liu Muhua, Yao Mingyin. Study on image recognition of insect pest of sugarcane cotton Aphis based on rough set and fuzzy Cmeans clustering［C］∥Proc of the 3rd International Symposium on Intelligent Information Technology Application(IITA 2009), 2009:553555.
［51］Sammany M,Medhat T.Dimensionality reduction using rough set approach for two neural networksbased applications［C］∥Proc of Rough Sets and Intelligent Systems Paradigms, 2007:639647.
［52］Guan Zexin,Tang Jian,Yang Baojun, et al. Study on recognition method of rice disease based on image［J］. Chinese Journal of Rice Science,2010,24(5):497502.(in Chinese)
［53］Zhang Hongtao,Mao Hanping,Han Lühua. Detection of live Sitophilus oryzae (L.) in stored wheat by nearinfrared hyperspectral imaging［J］. Transactions of the Chinese Society of Agricultural Engineering, 2012,28(8):263268.(in Chinese)
［54］Wang Keru. Diagnosis of crop disease,insect pest and weed based on image recognition［D］.Beijing:Chinese Academy of Agriculture Sciences,2005.(in Chinese)
附中文参考文献：
［2］韩思奇，王蕾.图像分割的阈值法综述［J］.系统工程与电子技术,2002,24(6):9194.
［3］穗波信雄.根据图像提取植物的生长信息［Z］.农业机械学会关西支部第6次支部研究资料,1989:12.
［4］陈佳娟,赵学笃.采用计算机视觉进行棉花虫害程度的自动测定［J］.农业工程学报,2001, 17(2):157160.
［6］段瑞玲,李庆祥,李玉和.图像边缘检测方法研究综述［J］.光学技术,2005,31（3）:415419.
［8］何丹丹,徐梅.基于多策略融合技术的水稻叶片边缘检测算法研究［J］.东北农业大学学报,2012,43(5):6568.
［11］王萍,唐江丰,王博,等. 基于数学形态学的植物叶片图像分割方法研究［J］. 浙江农业学报, 2012,24(3):509513.
［12］任磊,赖惠成,陈钦政,等.基于改进分水岭的棉花图像分割方法［J］.计算机工程与应用,2012,48（34）：207212.
［13］孙吉贵,刘杰,赵连宇.聚类算法研究［J］.软件学报,2008,19(1):4861.
［14］王守志,何东健,李文,等. 基于核K均值聚类算法的植物叶部病害识别［J］. 农业机械学报,2009,40（3）:152155.
［17］李震,洪添胜,曾祥业,等.基于Kmeans聚类的柑橘红蜘蛛图像目标识别［J］.农业工程学报,2012,28（23）:147153.
［18］刁智华,宋寅卯,王欢,等.基于植物病斑的图像分割研究综述［J］.农机化研究,2012, 10(10):111.
［19］赖军臣,汤秀娟,李少昆,等. 基于GMRF模型的玉米叶斑病害图像的分割［J］. 中国农业科学,2010, 43(7):13631369.
［20］袁媛,李淼,梁青，等. 基于水平集的作物病叶图像分割方法［J］. 农业工程学报,2011,27(2)：208212.
［21］虎晓红,李炳军,席磊. 基于多示例图的小麦叶部病害分割方法［J］. 农业工程学报,2012,28(13)：154159.
［24］张红涛,毛罕平,邱道尹.储粮害虫图像识别中的特征提取［J］.农业工程学报, 2009, 25(2):126130.
［26］徐贵力, 毛罕平, 李萍萍. 缺素叶片彩色图像颜色特征提取的研究［J］. 农业工程学报,2002,18（4）:150154.
［28］朱虹, 郑丽敏,尹健玲，等.基于冠层图像颜色特征提取的小麦氮营养水平评价［J］. 农业工程学报,2010, 26(2):1620.
［30］徐贵力,毛罕平,李萍萍.差分百分率直方图法提取缺素叶片纹理特征［J］.农业机械学报,2003,34(2):7679.
［32］谷庆魁. 基于计算机图像处理的玉米叶部病害识别系统［D］.沈阳:沈阳理工大学,2008.
［33］刘丽,匡纲要.图像纹理特征提取方法综述［J］.中国图像图形学报,2009, 14(4):622635.
［34］毛罕平,徐贵力，李萍萍.西红柿缺素叶片的图像特征提取和优化选择研究［J］.农业工程学报, 2003, 19(2):1.
［35］梁佳熙.基于图像处理的黄瓜霜霉病实验研究及应用［D］.长春:吉林大学,2011.
［37］王丽亚.图像的特征提取和分类［D］.西安：西安电子科技大学,2006.
［38］安冈善文.图像处理技术在环境中的应用［M］∥电气学会杂志特集,1985:455458.
［42］祈广云,马晓丹,关海鸥.采用改进遗传算法提取大豆叶片病斑图像［J］.农业工程学报,2009,25(5):142145.
［43］温芝元,曹乐平. 基于补偿模糊神经网络的脐橙不同病虫害图像识别［J］. 农业工程学报,2012,28 (11):152157.
［44］张学工.关于统计学习理论与支持向量机［J］.自动化学报,2000,26(1):3242.
［45］田有文,张长水,李成华.支持向量机在植物病斑形状识别中的应用研究［J］.农业工程学报, 2004,20(3):134136.
［46］田有文,牛妍.支持向量机在黄瓜病害识别中的应用研究［J］.农机化研究,2009(3):3639.
［47］刁智华.大田小麦叶部病害智能诊断系统研究与应用［D］.合肥:中国科学技术大学,2010.
［48］张建华,冀荣华,袁雪,等.基于径向基支持向量机的棉花虫害识别［J］.农业机械学报,2011,42(8):178183.
［49］杜瑞卿, 张征田,刘广亮,等. 粗糙集模糊聚类分析法在昆虫分类研究中的应用［J］. 昆虫学报,2006, 49(1):106111.
［52］管泽鑫,唐健,杨保军,等.基于图像的水稻病害识别方法研究［J］.中国水稻科学,2010,24(5):497502.
［53］张红涛,毛罕平,韩绿化.近红外高光谱成像技术检测粮仓米象活虫［J］.农业工程学报,2012, 28(8):263268.
［54］王克如.基于图像识别的作物病虫草害诊断研究［D］.北京:中国农业科学院,2005.

[1]	马冬梅, 黄欣悦, 李煜. 基于特征融合和注意力机制的图像语义分割[J]. 计算机工程与科学, 2023, 45(03): 495-503.
[2]	吴从中, 董浩, 方静. 基于注意力机制的自适应滤波遥感图像分割网络[J]. 计算机工程与科学, 2022, 44(11): 2010-2018.
[3]	刘从军, 徐佳陈, 肖志勇, 柴志雷. 基于深度学习的心脏核磁共振图像自动分割算法[J]. 计算机工程与科学, 2022, 44(09): 1646-1654.
[4]	张建伟, 周亚同, 史宝军, 何昊, 王文. 基于SSD算法的轻量化仪器表盘检测算法[J]. 计算机工程与科学, 2022, 44(08): 1418-1425.
[5]	仇静博, 燕雪峰, 汪俊, 郭延文, 魏明强, . 基于全卷积神经网络的单幅隧道图像裂纹提取算法[J]. 计算机工程与科学, 2022, 44(05): 845-854.
[6]	刘榕, 伍欣, 敖斌, 文青, 李宽. 用于CD56图像分割的细胞标注精细化与自适应加权损失[J]. 计算机工程与科学, 2022, 44(05): 870-878.
[7]	刘云, 郑文凤, 张轶. 代价约束算法对入侵检测特征提取的优化研究[J]. 计算机工程与科学, 2022, 44(03): 447-453.
[8]	谈恩民, 王晨. 基于表征学习的模拟电路故障诊断[J]. 计算机工程与科学, 2022, 44(01): 27-35.
[9]	姬子恒, 王斌. 基于深度学习的草图检索方法研究进展[J]. 计算机工程与科学, 2021, 43(12): 2190-2205.
[10]	王鑫, 廖祎玮, 赵国生, 王健, 谢宝文. 一种面向任务需求的群智感知任务分配模型[J]. 计算机工程与科学, 2021, 43(08): 1512-1520.
[11]	曾增峰, 环宇翔, 邹卓, 郑立荣. 多尺度深度监督的高度近视萎缩病变分割方法[J]. 计算机工程与科学, 2021, 43(07): 1264-1272.
[12]	蒋芸, 高静, 王发林. SAG-Net：用于联合视盘和视杯分割的新型跳过注意力指导网络[J]. 计算机工程与科学, 2021, 43(07): 1273-1282.
[13]	张俊鹏, 刘辉, 李清荣. 基于FCN-LSTM的工业烟尘图像分割[J]. 计算机工程与科学, 2021, 43(05): 906-916.
[14]	陈爱莲, 丁正龙, 詹曙. 基于对抗学习和多尺度特征融合的前列腺MR图像分割[J]. 计算机工程与科学, 2021, 43(04): 697-703.
[15]	朱倩倩, 车文刚, 苗晗. 数字化藏文古籍中多样性字体的实现方法研究[J]. 计算机工程与科学, 2020, 42(11): 2073-2079.