The grade of tea is closely related to tea quality, so the identification of tea grade is an important task. In order to improve the identification capability of the tea grade system, a fuzzy maximum uncertainty linear discriminant analysis (FMLDA) methodology was proposed based on maximum uncertainty linear discriminant analysis (MLDA). Based on FMLDA, a tea grade recognition system was established for the grade recognition of Chunmee tea. The process of this system is as follows: firstly, the near-infrared (NIR) spectra of Chunmee tea were collected using a Fourier transform NIR spectrometer. Next, the spectra were preprocessed using standard normal variables (SNV). Then, direct linear discriminant analysis (DLDA), maximum uncertainty linear discriminant analysis (MLDA), and FMLDA were used for feature extraction of the spectra, respectively. Finally, the k-nearest neighbor (KNN) classifier was applied to classify the spectra. The k in KNN and the fuzzy coefficient, m, were discussed in the experiment. The experimental results showed that when k = 1 and m = 2.7 or 2.8, the accuracy of the FMLDA could reach 98.15%, which was better than the other two feature extraction methods. Therefore, FMLDA combined with NIR technology is an effective method in the identification of tea grade.

The extraction of near‐infrared (NIR) spectral discrimination information is important for the NIR spectral classification task. Some discriminant information extraction algorithms such as linear discriminant analysis (LDA), uncorrelated discriminant transform (UDT), and fuzzy uncorrelated discriminant transform (FUDT) use the sample mean to calculate the total scattering matrix. However, the calculation of the sample mean will be affected by abnormal samples, which will affect the extraction of discriminant information. To solve this problem, this article proposes an improved discriminant information extraction algorithm called weighted global fuzzy uncorrelated discriminant transform (WGFUDT). The algorithm uses the Euclidean distance between the training samples to weight the training samples and assigns a smaller weight to the abnormal data to reduce its effect on the sample mean. The algorithm was used for the grade identification of two green teas (Huangshan Maofeng tea and Mee tea). The results show that the classification accuracies of WGFUDT on Mee tea and Huangshan Maofeng tea are 97.22% and 99.07%, respectively. Compared with LDA, UDT and FUDT, WGFUDT can obtain more spectral discriminant information and has higher accuracy in grade identification of Huangshan Maofeng tea and Mee tea. Practical Applications Some traditional discriminant information extraction algorithms sometimes cannot extract enough discriminant information, which will affect the recognition rate of tea grades. WGFUDT can extract more discriminant information in the face of green tea spectral information and achieve higher accuracy. WGFUDT for green tea grade identification is fast and effective.