-
农作物病害影响作物产量、粮食安全和国民经济[1]。病害预防是在病害发生早期快速、准确地发现和识别病害[2],因此,病害预防在农业生产中极为重要。然而,在大田作物中监测和鉴定植物病害是一项非常复杂的任务,通常通过人工目视诊断来实现。人工目视诊断是借助于专业知识、书籍或者互联网中关于植物病害的文字和图片描述来判断病害,但在实际生产过程中,人们判别植物病害时容易产生偏见、视错觉,导致偏差[3],并最终导致农药和杀菌剂使用不当[4]。同时,人工目视诊断也存在效率低、成本高等一系列问题。随着科学进步和新技术的引进,目前植物病害检测方法有基于脱氧核糖核酸的聚合酶链反应(Polymerase chain reaction, PCR),基于血清学方法的酶联免疫吸附试验(Enzyme linked immunosorbent assay, ELISA),基于分子生物学方法的荧光原位杂交(Fluorescence in situ hybridization, FISH)和免疫荧光(Immunofluorescence, IF),还有基于荧光显微镜(Fluorescence microscope)、流式细胞术(Flow cytometry, FC)和激光技术等方法[5],这些生物检测方法通常非常耗时,不能及时提供有效信息[6]。随着农业和现代化信息技术交互碰撞,相互联结,智能化农业快速发展,在许多国家使用计算机视觉技术对农业生产进行智能化管理已成为农业发展的主要趋势[7]。与传统方法相比,基于遥感的传感器以及成像技术应用于自动化病害识别过程更加迅捷、精确和实时,已成为农业现代化发展的研究热点[8]。笔者综述了包括图像处理、机器视觉和机器学习技术在内的计算机视觉识别植物病害技术的基本概念、研究现状和方法,并提出存在的问题和展望,为计算机视觉技术在植物病害识别上的应用和研究提供依据。
Advances in recognition of plant diseases based on computer vision
-
摘要: 随着农业和现代化信息技术的交互、联结和碰撞,农业逐渐趋于现代化、智能化和数字化,近年来运用计算机视觉技术对植物病害进行诊断得到广泛应用,比传统方法更加迅捷、精确。分别从图像采集、图像预处理、图像分割、图像特征提取、病害识别和分类5个方面进行阐述,总结了植物病害图像识别技术的要点及存在问题,并对其未来发展进行了展望,为计算机视觉技术在植物病害识别上的应用和研究提供依据。Abstract: Plant diseases restrict the development of agriculture in production, safety and economy. Monitoring plant health status and preventing plant diseases from occurrence are very important for sustainable agricultural development. With the interaction, connection and collision between agriculture and modern information technology, agriculture gradually tends to be modern, intelligent and digital. Computer vision has been widely used in detecting plant diseases in recent years, which is more rapid and accurate than traditional methods. The computer vision in recognition of plant diseases was reviewed from the aspects of image acquisition, image preprocessing, image segmentation, image feature extraction and disease recognition and classification, and its key points were summarized. Problems arising from and outlook on the image recognition of plant diseases based on computer vision were put forward to provide some reference for the application and research of computer vision in recognition of plant diseases in the future.
-
Key words:
- plant disease /
- computer vision /
- image processing /
- deep learning
-
[1] CORREDOR-MORENO P, SAUNDERS D G O. Expecting the unexpected: factors influencing the emergence of fungal and oomycete plant pathogens [J]. New Phytologist, 2020, 225(1): 118 − 125. doi: 10.1111/nph.16007 [2] VISHNOI V K, KUMAR K, KUMAR B. Plant disease detection using computational intelligence and image processing [J]. Journal of Plant Diseases and Protection, 2021, 128: 19 − 53. doi: 10.1007/s41348-020-00368-0 [3] BARBEDO J G A. A review on the main challenges in automatic plant disease identification based on visible range images [J]. Biosystems Engineering, 2016, 144: 52 − 60. doi: 10.1016/j.biosystemseng.2016.01.017 [4] SALEEM M H, KHANCHI S, POTGIETER J, et al. Image-based plant disease identification by deep learning meta-architectures [J]. Plants (Basel), 2020, 9(11): 1451. [5] YVON M, THЁBAUD G, ALARY R, et al. Specific detection and quantification of the phytopathogenic agent 'Candidatus Phytoplasma prunorum' [J]. Molecular and Cellular Probes, 2009, 23(5): 227 − 234. doi: 10.1016/j.mcp.2009.04.005 [6] SANKARAN S, MISHRA A, EHSANI R, et al. A review of advanced techniques for detecting plant diseases [J]. Computers and Electronics in Agriculture, 2010, 72(1): 1 − 13. doi: 10.1016/j.compag.2010.02.007 [7] ELAHI E, WEIJUN C, ZHANG H, et al. Agricultural intensification and damages to human health in relation to agrochemicals: Application of artificial intelligence [J]. Land Use Policy, 2019, 83: 461 − 474. doi: 10.1016/j.landusepol.2019.02.023 [8] MOHANTY S P, HUGHES D P, SALATHÉ M. Using deep learning for image-based plant disease detection [J]. Frontiers in Plant Science, 2016, 7: 1419. doi: 10.3389/fpls.2016.01419 [9] PHADIKAR S, SIL J, DAS A K. Classification of rice leaf diseases based on morphological changes [J]. International Journal of Information and Electronics Engineering, 2012, 2(3): 460 − 463. [10] 陈佳娟, 纪寿文, 李娟, 等. 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. [11] 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. [12] LU J, EHSANI R, SHI Y, et al. Detection of multi-tomato leaf diseases (late blight, target and bacterial spots) in different stages by using a spectral-based sensor [J]. Science Reports, 2018, 8(1): 2793. doi: 10.1038/s41598-018-21191-6 [13] 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 [14] HUGHES D P, SALATHÉ M. An open access repository of images on plant health to enable the development of mobile disease diagnostics [J]. Computer Science, arXiv preprint arXiv:, 1511, 08060v2: 2016. [15] 许良凤, 徐小兵, 胡敏, 等. 基于多分类器融合的玉米叶部病害识别[J]. 农业工程学报, 2015, 31(14): 194 − 201. [16] KAUR S, PANDEY S, GOEL S. Semi-automatic leaf disease detection and classification system for soybean culture [J]. IET Image Processing, 2018, 12(6): 1038 − 1048. doi: 10.1049/iet-ipr.2017.0822 [17] PUJARI J D, YAKKUNDIMATH R, BYADGI A S. Recognition and classification of produce affected by identically looking powdery mildew disease [J]. Acta Technologica Agriculturae, 2014, 17(2): 29 − 34. doi: 10.2478/ata-2014-0007 [18] HALLAU L, NEUMANN M, KLATT B, et al. Automated identification of sugar beet diseases using smartphones [J]. Plant Pathology, 2018, 67(2): 399 − 410. doi: 10.1111/ppa.12741 [19] CRUZ A, AMPATZIDIS Y, PIERRO R, et al. Detection of grapevine yellows symptoms in Vitis vinifera L. with artificial intelligence [J]. Computers and Electronics in Agriculture, 2019, 157: 63 − 76. doi: 10.1016/j.compag.2018.12.028 [20] PANTAZI X E, MOSHOU D, TAMOURIDOU A A. Automated leaf disease detection in different crop species through image features analysis and one class classifiers [J]. Computers and Electronics in Agriculture, 2019, 156: 96 − 104. doi: 10.1016/j.compag.2018.11.005 [21] 王双喜, 董晓志, 王旭. 温室植物病害数字化处理中图像增强方法的研究[J]. 内蒙古农业大学学报(自然科学版), 2007, 28(3): 15 − 18. [22] MESEJO P, IBÁÑEZ Ó, CORDÓN Ó, et al. A survey on image segmentation using metaheuristic-based deformable models: State of the art and critical analysis [J]. Applied Soft Computing., 2016, 44: 1 − 29. doi: 10.1016/j.asoc.2016.03.004 [23] 汪京京, 张武, 刘连忠, 等. 农作物病虫害图像识别技术的研究综述[J]. 计算机工程与科学, 2014, 36(7): 1363 − 1370. [24] SHINDE R C, JIBU M C, PATIL C Y. Segmentation technique for soybean leaves disease detection [J]. International Journal of Advanced Research, 2015, 3(5): 522 − 528. [25] 明浩, 苏喜友. 利用特征分割和病斑增强的杨树叶部病害识别[J]. 浙江农林大学学报, 2020, 37(6): 1159 − 1166. [26] 张会敏, 谢泽奇, 张善文, 等. 基于WT-Otsu算法的植物病害叶片图像分割方法[J]. 江苏农业科学, 2017, 45(18): 194 − 196. [27] 赵辉, 芮修业, 岳有军, 等. 复杂背景下基于AD-GAC模型和最大熵阈值法的叶片病斑分割[J]. 江苏农业科学, 2019, 47(18): 136 − 140. [28] 张芳, 王璐, 付立思, 等. 复杂背景下黄瓜病害叶片的分割方法研究[J]. 浙江农业学报, 2014, 26(5): 1346 − 1355. [29] BASHIR K, REHMAN M, BARI M. Detection and classification of rice diseases: An automated approach using textural features [J]. Mehran Univ Res J Sci Technol, 2019, 38(1): 239 − 250. doi: 10.22581/muet1982.1901.20 [30] 毛罕平, 张艳诚, 胡波. 基于模糊C均值聚类的作物病害叶片图像分割方法研究[J]. 农业工程学报, 2008, 24(9): 136 − 140. [31] BAI X, LI X, FU Z, et al. A fuzzy clustering segmentation method based on neighborhood grayscale information for defining cucumber leaf spot disease images [J]. Computers and Electronics in Agriculture, 2017, 136: 157 − 165. doi: 10.1016/j.compag.2017.03.004 [32] 温长吉, 王生生, 于合龙, 等. 基于改进蜂群算法优化神经网络的玉米病害图像分割[J]. 农业工程学报, 2013, 29(13): 142 − 149. [33] 王振, 师韵, 李玉彬. 基于改进全卷积神经网络的玉米叶片病斑分割[J]. 计算机工程与应用, 2019, 55(22): 127 − 132. [34] SINGH V, MISRA A K. Detection of plant leaf diseases using image segmentation and soft computing techniques [J]. Information Processing in Agriculture, 2017, 4(1): 41 − 49. doi: 10.1016/j.inpa.2016.10.005 [35] SHARIF M, KHAN M A, IQBAL Z, et al. Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection [J]. Computers and Electronics in Agriculture, 2018, 150: 220 − 234. doi: 10.1016/j.compag.2018.04.023 [36] 濮永仙. 计算机视觉在作物病害诊断中的研究进展[J]. 智能计算机与应用, 2015, 5(2): 68 − 72. [37] 彭可为, 李婵, 曹学仁, 等. 数字图像技术在植物病害自动识别中的研究进展[J]. 江西农业学报, 2012, 24(9): 69 − 71. [38] 刘丽娟, 刘仲鹏. 基于改进BP算法的玉米叶部病害图像识别研究[J]. 江苏农业科学, 2013, 41(11): 139 − 142. [39] 赵进辉, 罗锡文, 周志艳. 基于颜色与形状特征的甘蔗病害图像分割方法[J]. 农业机械学报, 2008, 39(9): 100 − 103. [40] BARBEDO J G A, KOENIGKAN L V, SANTOS T T. Identifying multiple plant diseases using digital image processing [J]. Biosystems Engineering, 2016, 147: 104 − 116. doi: 10.1016/j.biosystemseng.2016.03.012 [41] CHOUHAN S S, SINGH U P, JAIN S. Applications of computer vision in plant pathology: A Survey [J]. Archives of Computational Methods in Engineering, 2019, 27(2): 611 − 632. [42] PYDIPATI R, BURKS T F, LEE W S. Identification of citrus disease using color texture features and discriminant analysis [J]. Computers and Electronics in Agriculture, 2006, 52(1/2): 49 − 59. [43] VIJAYALAKSHMI B, MOHAN V. Kernel-based PSO and FRVM: An automatic plant leaf type detection using texture, shape, and color features [J]. Computers and Electronics in Agriculture, 2016, 125: 99 − 112. doi: 10.1016/j.compag.2016.04.033 [44] HUANG K Y. Application of artificial neural network for detecting Phalaenopsis seedling diseases using color and texture features [J]. Computers and Electronics in Agriculture, 2007, 57(1): 3 − 11. [45] 谭克竹, 沈维政. 基于BP神经网络的大豆叶片病害诊断模型的研究[J]. 自动化技术与应用, 2013, 32(12): 5 − 7. [46] 李颀, 赵洁, 杨柳, 等. 基于GA-BP神经网络和特征向量优化组合的黄瓜叶片病斑识别[J]. 浙江农业学报, 2019, 31(3): 487 − 495. [47] 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. [48] BURGOS-ARTIZZU X P, RIBEIRO A, TELLAECHE A, et al. Improving weed pressure assessment using digital images from an experience-based reasoning approach [J]. Computers and Electronics in Agriculture, 2009, 65(2): 176 − 185. doi: 10.1016/j.compag.2008.09.001 [49] 吕盛坪, 李灯辉, 冼荣亨. 深度学习在我国农业中的应用研究现状[J]. 计算机工程与应用, 2019, 55(20): 24 − 33. [50] 王聃, 柴秀娟. 机器学习在植物病害识别研究中的应用[J]. 中国农机化学报, 2019, 40(9): 171 − 180. [51] 周长建, 司震宇, 邢金阁, 等. 基于Deep Learning网络态势感知建模方法研究[J]. 东北农业大学学报, 2013, 44(5): 144 − 149. [52] SLADOJEVIC S, ARSENOVIC M, ANDERLA A, et al. Deep neural networks based recognition of plant diseases by leaf image classification [J]. Computational Intelligence and Neuroscience, 2016, 2016: 3289801. [53] 秦丰, 刘东霞, 孙炳达, 等. 基于深度学习和支持向量机的4种苜蓿叶部病害图像识别[J]. 中国农业大学学报, 2017, 22(7): 123 − 133. [54] 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. [55] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J]. Computer Science, arXiv preprint arXiv., 1409, 1556v6: 2015. [56] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions [J]. Computer Science, arXiv preprint arXiv., 1409, 4842v1: 2014. [57] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84 − 90. doi: 10.1145/3065386 [58] SUN W, YAO B, CHEN B, et al. Noncontact surface roughness estimation using 2D complex wavelet enhanced ResNet for Intelligent evaluation of milled metal surface quality [J]. Applied Sciences, 2018, 8(3): 381. doi: 10.3390/app8030381 [59] 钱晔, 李超, 李彤, 等. 基于Android手机系统的月季病虫害智能系统研究[J]. 北方园艺, 2019(10): 151 − 157. [60] 王衍安, 李明, 王丽辉, 等. 果树病虫害诊断与防治专家系统知识库的构建[J]. 山东农业大学学报(自然科学版), 2005, 36(3): 154 − 159. [61] 屈赟, 陶晡, 张文静. 基于Android系统手机的苹果病虫害专家诊断系统设计[J]. 北方园艺, 2015(19): 202 − 205.