Hierarchical Palette Extraction Based on Local Distinctiveness and Cluster Validation for Image Recoloring
Ju-Mi Kang, Youngbae Hwang · 2018
Palette-based image recoloring is one of the popular color manipulation methods by transforming dominant scene colors into corresponding user-specific colors intuitively. Because conventional palette extraction methods are based only on global color distribution, they cannot deal with local distinctive colors, which can cause not only the degraded result of image recoloring, but also the limitation of user selection. In this paper, we propose a new palette extraction method by iterative palette partitioning based on cluster validation. To find candidate colors for palette partitioning, we compute patch uniformity for local patches. For image recoloring with extracted palette, we use a statistics-based color transfer method by considering the pixel-wise weight from palette colors. In the experiments, our automatic or user-specific palette extraction shows more plausible palette representation than previous methods. Furthermore, image recoloring results show the effectiveness of the proposed method in terms of quality of color transfer and user experience.