Fast color quantization using MacQueen’s k-means algorithm

Abstract

Color quantization (CQ) is an important operation with many applications in computer graphics and image processing and analysis. Clustering algorithms have been extensively applied to this problem. However, despite its popularity as a general purpose clustering algorithm, k-means has not received much attention in the CQ literature because of its high computational requirements and sensitivity to initialization. In this paper, we propose a novel CQ method based on an online k-means formulation due to MacQueen. The proposed method utilizes adaptive and efficient cluster center initialization and quasirandom sampling to attain deterministic, high speed, and high-quality quantization. Experiments on a diverse set of publicly available images demonstrate that the proposed method is significantly faster than the more common batch k-means formulation due to Lloyd while delivering nearly identical results.