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)

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)