The current study is aimed to investigate how fabrics' tactile properties can be perceived through products' visual representations. Two major steps are taken to unveil the visual compensatory mechanism. The first step is to describe the mechanism. A novel method based on rough sets and fuzzy sets theories is proposed to extract principal visual features for each tactile property. In this part, the single-to-single and multiple-to-single correlations are studied by applying this method. The second step is to quantify the explored mechanism. A mathematical model between each tactile property and the corresponding principal Visual features is established using an adaptive network-based fuzzy inference system (ANFIS). This model has been proved to be capable of predicting fabrics' tactile properties from the perceived visual features with a satisfactory accuracy.
展开▼
