Silhouette extract from human body image based on color clustering analysis

Silhouette of a human body carries lots of important information, and many measures required for garment design can be taken directly from it. In this paper,, silhouette extraction from human body color image was focused. The clustering centers of color were determined from the gray histograms of RGB color space. The clustering analysis was carried out based on Euclidean distance. The images were further processed by using the algorithms of filling holes, closing and erosion, and the silhouettes were extracted from the processed images. The extracted smooth and closed silhouettes confirmed that the proposed method was effective to process human body images.