Fuzzy classification of luster of textile fabrics

The appearance of fabric is very important when a customer makes a choice for outer apparel. One of the factors that has an effect on the users’ judgment and on the appearance of the fabric is the luster of textiles. The luster can be considered as one of the most effective and essential factors of investigating the appearance of a fabric that is used by a consumer. In order to determine textile luster, there are different methods based on classic definitions; the ones based on image processing have results closer to human impressions of the fabric. Nevertheless, all the determining methods give numerical luster indexes which are far from the reality of a human’s impression, which is a qualitative one for luster. One method that can be used to transform numerical data to qualitative data is fuzzy logic for the classification of data for the luster index. In the presented method, after indicating luster index by the use of image processing, different fabric samples are classified in six different classes based on the luster determined by judgment of ten different inspectors. The luster index is finally classified in six fuzzy classes based on fuzzy logic theory. Results show that fuzzy classification is confirmed by viewers’ judgments.