The study results show that Multiple Regression Method can be used successfully to establish 6 prediction models, including fabric primary textures of “Thin-Thick”, “Cool-Warm”, “Exquisite-Wild”, “Bright-Dark” , “Simple-Complex” and “Overall Textures”, having discriminant coefficient of 0.66,0.71,0.57,0.65,0.67 and 0.70, respectively. Therefore, all the 6 models have good fitted ability.