Abstract:The accurate identification of tea varieties is of great significance to ensure the interests of tea producers and consumers. As a non-destructive or micro damage detection method, laser-induced breakdown spectroscopy (LIBS) has been widely used in the quality detection or classification of agricultural products and food. The objective of this research was to automatically select optimal spectral peaks from the full LIBS spectra, and develop effective classification model for identifying tea varieties. The LIBS spectra covering the region 200-500 nm were measured for 600 Chinese tea leaves including six varieties (i.e. Longjing green tea, Jinhao black tea, Tie Guanyin, Huang Jinya, White peony tea, and Anhua dark tea). A total of 50 optimal spectral peaks were automatically selected from full LIBS spectra (6102) by using the uninformative variable elimination (UVE) and partial least squares projection analysis, and the selected spectral peaks mainly represent the elemental difference in C, Fe, Mg, Mn, Al and Ca. Partial Least Squares Discriminant Analysis (PLS-DA) was used for developing classification model using selected optimal spectral peaks, and yielded the 99.77% classification accuracy for 300 test samples was reached. The results indicate that the proposed method can be used to identify leaf varieties in various tea products.