Improving the performance of k-means for color quantization

Color quantization is an important operation with many applications in graphics and image processing. Most quantization methods are essentially based on data clustering algorithms. However, despite its popularity as a general purpose clustering algorithm, k-means has not received much respect in the color quantization literature because of its high computational requirements and sensitivity to initialization. In this paper, we investigate the performance of k-means as a color quantizer. We implement fast and exact variants of k-means with several initialization schemes and then compare the resulting quantizers to some of the most popular quantizers in the literature. Experiments on a diverse set of images demonstrate that an efficient implementation of k-means with an appropriate initialization strategy can in fact serve as a very effective color quantizer.

Research Highlights
► k-means clustering algorithm is investigated from a color quantization perspective.
► Fast and exact k-means variants that utilize data reduction, sample weighting, and accelerated nearest neighbor search are introduced.
► Presented k-means implementations outperformed state-of-the-art quantization methods on classic test images.
► Other advantages of the presented methods include ease of implementation, high computational speed, and the possibility of incorporating spatial information.