Search

Color quantization is an important operation with numerous 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, a fast color quantization method based on K-means is presented. The method involves several modifications to the conventional (batch) K-means algorithm, including data reduction, sample weighting, and the use of the triangle inequality to speed up the nearest-neighbor search. Experiments on a diverse set of images demonstrate that, with the proposed modifications, K-means becomes very competitive with state-of-the-art color quantization methods in terms of both effectiveness and efficiency.

Vector operators based on robust order statistics have proved successful in digital multichannel imaging applications, particularly color image filtering and enhancement, in dealing with impulsive noise while preserving edges and fine image details. These operators often have very high computational requirements, which limits their use in time-critical applications. This paper introduces techniques to speed up vector filters using the minimax approximation theory. Extensive experiments on a large and diverse set of color images show that proposed approximations achieve an excellent balance among ease of implementation, accuracy, and computational speed.