Recoloring textile fabric images based on improved fuzzy clustering |
| |
| Authors: | Zhe Zou Hui‐Liang Shen Xin Du Sijie Shao John H. Xin |
| |
| Affiliation: | 1. College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China;2. Institute of Textiles and Clothing, the Hong Kong Polytechnic University, Hong Kong, China |
| |
| Abstract: | This article proposes a new recoloring method for textile fabric images based on improved fuzzy local information c‐means (FLICM) clustering. In the clustering algorithm, the fuzzy factor was modified so that it can produce reliable segmentation in areas with rich details. With the obtained cluster labels and pixel‐wise memberships, the color of each pixel is modeled as the linear combination of the two most dominant colors. The recoloring process was then conducted by replacing the specified dominant color with user‐provided target colors. Experimental results showed that the proposed method can produce natural and faithful color appearance on both printed and yarn‐dyed fabric images, and outperforms the state‐of‐the‐art. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 115–123, 2017 |
| |
| Keywords: | coloration recoloring color theme design textile fabric image fuzzy clustering image segmentation |
|
|
