On selection of centroids of fuzzy clusters for color classification
This work addresses color classification challenges in image processing, but it is incremental as it builds on existing fuzzy c-means algorithms.
The authors tackled the problem of initializing centroids in fuzzy c-means for color clustering by proposing a method that extracts dominant, vivid colors as initial centroids, resulting in improved clustering performance.
A novel initialization method in the fuzzy c-means (FCM) algorithm is proposed for the color clustering problem. Given a set of color points, the proposed initialization extracts dominant colors that are the most vivid and distinguishable colors. Color points closest to the dominant colors are selected as initial centroids in the FCM. To obtain the dominant colors and their closest color points, we introduce reference colors and define a fuzzy membership model between a color point and a reference color.