VARIANCE-CUT: A fast color quantization method based on hierarchical clustering

Color quantization is an important operation with many applications in graphics and image processing. Clustering algorithms have been extensively applied to this problem. In this paper, we propose a simple yet effective color quantization method based on divisive hierarchical clustering. Our method utilizes the commonly used binary splitting strategy along with several carefully selected heuristics that ensure a good balance between effectiveness and efficiency. We also propose a slightly computationally expensive variant of this method that employs local optimization using the Lloyd-Max algorithm. Experiments on publicly available test images demonstrate that the proposed method outperforms some of the most popular quantizers in the literature.