Abstract: Three quantitative analysis models for fresh tea leaves, including moisture, total nitrogen and crude fiber, were built by applying near infrared spectroscopy combined with partial squares (NIR-PLS) , in order to analyze the quality of the fresh tea leaves, class correlation model based on three main contents by BP-ANN were built. Results showed that both the calibration samples and the prediction samples of models had acquired a high fitting degree, the value of RPwere 0.9109, 0.8989, 0.8895, RMSEP were 0.361, 0.103, 0.195.Based on the high correlation between near-infrared spectroscopy, fresh tea leaves component and class, class model were built by NIR-PLS, the discrimination ratio were 93.10%, the model had high prediction precision.This provided a new way of thinking for quality analysis and class rapid evaluation of tea leaf materials.