基于PCA-LDASVM算法的茶小绿叶蝉识别

doi:10.13733/j.jcam.issn.2095-5553.2024.01.040

摘要/Abstract

摘要： 为提高茶小绿叶蝉病虫害的识别效率和精度，提出一种基于PCALDASVM的茶小绿叶蝉病虫害识别方法。首先，对采集的茶叶图像进行预处理，得到缩放后的图像；然后，利用主成分分析(PCA)对预处理后的图像提取全局特征，降低特征数据的维度，从而减少后续的计算时间；再利用线性判别分析(LDA)寻找特征数据的最优投影空间，使类内散布距离最小，类间散布距离最大，进一步提高识别的准确率和精确度；最后，利用支持向量机(SVM)分类器进行分类识别。试验结果表明，PCALDASVM模型识别准确率达96%，精确度达100%，召回率达92%，整体识别性能优于SVM，BP，KNN，PCASVM模型，具备一定的理论价值和参考意义。

关键词: 茶小绿叶蝉, 病虫害识别, 主成分分析(PCA), 线性判别分析(LDA), 支持向量机(SVM)

Abstract: In order to solve the efficiency and accuracy of Empoasca Flavescens recognition, a recognition method based on PCALDASVM is proposed. Firstly, the collected tea image are preprocessed and the scaled image is obtained. Then, Principal Component Analysis (PCA) is used to extract global features from the preprocessed image to reduce the dimension of feature data, so as to reduce the subsequent calculation time. Linear Discriminant Analysis (LDA) is used to find the optimal projection space of feature data to minimize the intra class dispersion distance and maximize the inter class dispersion distance, so as to further improve precision and accuracy of recognition. Finally, Support Vector Machine (SVM) classifier is used for classification and recognition. The experimental results show that the recognition accuracy of PCALDASVM model can reach 96%, precision can reach 100%, and recall can reach 92%. The overall recognition performance is better than that of SVM，BP，KNN，PCASVM model, which has certain theoretical value and reference significance.

Key words: Empoasca Flavescens, pest recognition, Principal Component Analysis(PCA), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM)

中图分类号:

TP391.4: S432

吴鹏, 刘金兰. 基于PCA-LDASVM算法的茶小绿叶蝉识别[J]. 中国农机化学报, 2024, 45(1): 295-300.

Wu Peng, Liu Jinlan. Recognition of Empoasca Flavescens based on PCA-LDA-SVM algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(1): 295-300.

参考文献

［1］王杰, 童璐, 巨学阳, 等. 茶树对茶小绿叶蝉为害的响应及其机制研究进展［J］. 福建农林大学学报(自然科学版), 2021, 50(2): 145-154.
Wang Jie, Tong Lu, Ju Xueyang, et al. Progress on the induced defense of tea plants (Camellia sinensis) in response to the attack of tea green leafhopper (Empoasca onukii) and its mechanism ［J］. Journal of Fujian Agriculture and Forestry University (Natural Science Edition), 2021, 50(2): 145-154.
［2］史庆才, 李向阳, 陈志伟, 等. 茶园假眼小绿叶蝉的防控技术研究进展［J］. 农学学报, 2015, 5(1): 20-24.
Shi Qingcai, Li Xiangyang, Chen Zhiwei, et al. Advances on prevention and control technology of Empoasca vitis Gthe in tea garden ［J］. Journal of Agriculture, 2015, 5(1): 20-24.
［3］ Wu L Y, Jin S, Wu M Y, et al. Advances in tea leafhopper integrated pest management ［J］. Guizhou Agricultural Sciences, 2014, 42(3): 64-68.
［4］陈立杰. 茶叶实用技术［M］. 贵阳: 贵州大学出版社, 2018.
［5］陈晶, 朱启兵, 黄敏, 等. 基于机器视觉的茶小绿叶蝉识别方法研究［J］. 激光与光电子展, 2018, 55(1): 342-349.
Chen Jing, Zhu Qibin, Huang Min, et al. Recognition of Empoasca Flavescens based on machine vision ［J］. Laser & Optoelectronics Progress, 2018, 55(1): 342-349.
［6］陈梅香, 杨信廷, 石宝才, 等. 害虫自动识别与计数技术研究进展与展望［J］. 环境昆虫学报, 2015, 37(1): 176-183.
Chen Meixiang, Yang Xinting, Shi Baocai, et al. Research progress and prospect of technologies for automatic identifying and counting of pests ［J］. Journal of Environmental Entomology, 2015, 37(1): 176-183.
［7］张燕, 田国英, 杨英茹, 等. 基于SVM的设施番茄早疫病在线识别方法研究［J］. 农业机械学报, 2021, 52(S1): 125-133, 206.
Zhang Yan, Tian Guoying, Yang Yingru, et al. Online detection method of tomato early blight disease based on SVM ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 125-133, 206.
［8］刘翠翠, 杨涛, 马京晶, 等. 基于PCASVM的麦冬叶部病害识别系统［J］. 中国农机化学报, 2019, 40(8): 132-136.
Liu Cuicui, Yang Tao, Ma Jingjing, et al. Identification system for leaf diseases of Ophiopogon japonicus based on PCASVM［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(8): 132-136.
［9］马佳佳, 陈友鹏, 王克强, 等. 基于优化SVM的虫害图像识别研究［J］. 中国粮油学报, 2022(5): 10-15.
Ma Jiajia, Chen Youpeng, Wang Keqinag, et al. Research on insect pest image recognition based on optimized SVM ［J］. Journal of the Chinese Cereals and Oils Association, 2022(5): 10-15.
［10］张娜, 刘坤, 韩美林, 等. 一种基于PCA和LDA融合的人脸识别算法研究［J］. 电子测量技术, 2020, 43(13): 72-75.
Zhang Na, Liu Kun, Han Meilin, et al. Research on face recognition algorithm based on PCA and LDA ［J］. Electronic Measurement Technology, 2020, 43(13): 72-75.
［11］王健峰, 张磊, 陈国兴, 等. 基于改进的网格搜索法的SVM参数优化［J］. 应用科技, 2012, 39(3): 28-31.
Wang Jianfeng, Zhang Lie, Chen Guoxing, et al. A parameter optimization method for an SVM based on improved grid search algorithm ［J］. Applied Science and Technology, 2012, 39(3): 28-31.
［12］张强, 贾宝山, 董晓雷, 等. PCAGASVM的回采工作面瓦斯涌出量预测［J］. 辽宁工程技术大学学报(自然科学版), 2015, 34(5): 572-577.
Zhang Qiang, Jia Baoshan, Dong Xiaolei, et al. Working face gas emission prediction based on PCAGASVM ［J］. Journal of Liaoning Technical University (Natural Science), 2015, 34(5): 572-577.
［13］赵东东, 赵雅丽, 赵秉强, 等. 基于PCALSTM小麦叶片水分检测研究［J］. 中国农机化学报, 2019, 40(3): 154-158, 184.
Zhao Dongdong, Zhao Yali, Zhao Bingqiang, et al. Study on wheat leaf moisture detection based on PCALSTM ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(3): 154-158, 184.
［14］ Tang J, Yu W, Chai T, et al. Online principal component analysis with application to process modeling ［J］. Neurocomputing, 2012, 82: 167-178.
［15］ Yu Z, Fang H, Zhang J Q, et al. Hyperspectral imaging technology combined with deep learning for hybrid okra seed identification ［J］. Biosystems Engineering, 2021, 212: 46-61.
［16］ Lu J, Plataniotis K N, Venetsanopoulos A N. Face recognition using LDAbased algorithms ［J］. IEEE Transactions on Neural Networks, 2003, 14(1): 195-200.
［17］ Khanmohammadi M, Karami F, MirMarqués A, et al. Classification of persimmon fruit origin by near infrared spectrometry and least squaressupport vector machines ［J］. Journal of Food Engineering, 2014, 142: 17-22.
［18］ Li D, Shi R, Yao N, et al. Realtime patientspecific ECG arrhythmia detection by quantum genetic algorithm of least squares twin SVM ［J］. Journal of Beijing Institute of Technology, 2020, 29(1): 29-37.
［19］吴昊昱. 基于小样本学习的自然场景图像中茶叶病害识别［D］. 合肥: 安徽大学, 2020.
［20］ Dirbaz M, Allahviranloo T. Fuzzy multiquadric radial basis functions for solving fuzzy partial differential equations ［J］. Computational and Applied Mathematics, 2019, 38: 1-19.
［21］魏锋涛, 卢凤仪. 融合核函数在改进径向基代理模型中的应用［J］. 计算机工程与应用, 2019, 55(7): 58-65.
Wei Fengtao, Lu Fengyi. Application of hybrid kernel function in improved radial basis function Meta model ［J］. Computer Engineering and Applications, 2019, 55(7): 58-65.
［22］王杰, 程学新, 彭金柱. 一种基于粒子群算法优化的加权随机森林模型［J］. 郑州大学学报(理学版), 2018, 50(1): 72-76.
Wang Jie, Cheng Xuexin, Peng Jinzhu. A weighted random forest model based on particle swarm optimization ［J］. Journal of Zhengzhou University (Natural Science Edition), 2018, 50(1): 72-76.
［23］徐竟泽, 吴作宏, 徐岩, 等. 融合PCA、LDA和SVM算法的人脸识别［J］. 计算机工程与应用, 2019, 55(18): 34-37.
Xu Jingze, Wu Zuohong, Xu Yan, et al. Face recognition based on PCA, LDA and SVM algorithms ［J］. Computer Engineering and Applications, 2019, 55(18): 34-37.

[1]	王江晴, 冀星, 莫海芳, 帖军, 刘畅, . 基于轻量化VGG的植物病虫害识别[J]. 中国农机化学报, 2022, 43(4): 25-31.
[2]	吴丹, 刘永华, 吴玉娟. 基于LoRa和SVM-Markov的蓝莓园精准灌溉系统研究[J]. 中国农机化学报, 2022, 43(11): 203-208.
[3]	陆雅诺;陈炳才;. 基于注意力机制的小样本啤酒花病虫害识别[J]. 中国农机化学报, 2021, 42(3): 189-196.