As the most widely used material in footwear, leather has its unique texture and hand feeling which could improve the quality of the products. On the basis of Kansei Engineering, this study analyzes the features of shoe leathers, including colors and textures, and then expresses the vision and visual-tactile imagery of the consumers on the types of leathers through articificial neural network verification. This paper also provides suggestions for footwear designers and the leather manufacturers on the design and selection of leather to accelerate the design flow, to assist the designers with the selection of the suitable materials in an objective way, and to promote the innovative competitiveness of the footwear eventually. This study firstly lists the representative words of the consumers on vision and visual-tactile sense perception on leather of footwear, and makes a quantitatively compilation about the vision and visual-tactile sense perception. What’s more, a program is written to capture the essential color and adhesion degree of the photo colors of these leather samples as color features. Then, the gray-scale values of the image are analyzed, and the related computational methods of LBP, SCOV, VAR and SAC are put forward on the basis of pixel eight-neighborhood to capture the textural features of the images. Taking the captured eigenvalue of color and texture as input layer and the quantized values of the perceptual words as output layer, The specific achievements of the study are as follows: a better Kansei engineering and articificial neural network training method of shoe leather is proposed, and an aided design flow of shoe leather with perceptual words and back propagation articificial neural network are worked out.
Human computer interaction, Kansei engineering, articificial neural network, color feature, texture feature