Along with the trend toward automation in the textile industry, an objective, correct. and efficient fiber identification method has become an important component of rapid respondent systems the textile industry desires. Using a polyester/cellulose nonwoven fabric, currently the highest in demand in the market, as the material and applying a combined stain test and regression method, an identification model for nonwoven blending ratios is established in this study. The results clearly indicate that with regression, CIE L*a*b*c*h can be used to establish the required identification model for polyester/ cellulose nonwoven blending ratios. The correlation coefficient between the predicted regression value and the actual blending ratio is more than 0.99, indicating that the model's fitting ability is extremely high.