Unsupervised Color Classification for Yarn-dyed Fabric Based on FCM Algorithm

A novel method for realizing the color classifying in yarn-dyed fabric is proposed in this paper. The color image of yarn-dyed fabric was obtained by a flat scanner, and then it is converted from RGB color space to Lab color space. By analyzing the difference among RGB, HSL and Lab color space, the advantages of Lab color are concluded. FCM was selected as the Color Cluster method. A better color classification quality in Lab color space is shown in the experiment. The color yarn number is detected based on the validity for FCM clusters. Experimental comparisons on RGB, HSL, and Lab color spaces show that the approach proposed in this article is more effective for color extracting and classifying in yarn-dyed fabric.