Abstract: At present, most perceptual research approaches the design issue directly from imagery to design features, while we are lack of such perceptual research characteristic of backward induction based on the design source code ofimage inducement. For the sake of the user and through combining perceptual fuzzy factor evaluation and cluster analysis, this paper puts forward a method of screening the design source code of backward image inducement, extracting the feature of pattern design source code which triggers the user’s perceptual image. Firstly, the data samples are screened to establish a sample perceptual semantic space, and the basic factors are selected by the fit evaluation method. Secondly, the fuzzy factor evaluation is used to determine the evaluation and reliability of the factor weight acquisition pattern set, and the pattern design source code feature set is screened with the factor taken as the evaluation criterion in combination with the cluster analysis. Finally, the validity and feasibility of the method are verified by T-test, taking the Miao costume pattern as a case study. The results show that the method can effectively guide the establishment of the source code feature set based on the perceptual cognitive theory.

Key words:  perceptual image, design source code, cluster analysis, fuzzy factor evaluation, sample source image