Abstract

When purchasing clothes, people always rely on intuition or follow the fashion trend for color selection. People never understand how to select the right color to match with them. A systematic method for detecting skin colors for clothes is proposed in this study. In the method, face recognition with considerable images was first discussed. Next, the innovative method of capturing color with points was used along with making complexion aggregated analysis. In the study, RGB was conversed to be the Lab space for the collected data which were then analyzed based on fuzzy clustering to get grouping. The results are presented in the final grouping lab value and RGB index. In addition, a Face RGB program was constructed to capture color automatically from 12000 images. Some 17 clustering results were obtained by the Color FCM program constructed in this study. The results can be used to select the customized color of clothes and an expert system can further be made in the future.

Keywords: Skin color; Clothes; Fuzzy C-Means; Big data