8 December 2015 In search of a new initialization of K-means clustering for color quantization
Author Affiliations +
Proceedings Volume 9875, Eighth International Conference on Machine Vision (ICMV 2015); 987506 (2015) https://doi.org/10.1117/12.2228712
Event: Eighth International Conference on Machine Vision, 2015, Barcelona, Spain
Abstract
Color quantization is still an important auxiliary operation in the processing of color images. The K-means clustering (KM), used to quantize the color, requires an appropriate initialization. In this paper, we propose a combined KM method that use to initialize the results of well-known quantization algorithms such as Wu's, NeuQuant (NQ) and Neural Gas (NG). This approach, assessed by three quality indices: PSNR, ΔE and ΔM, improves the results. Experimental results of such combined quantization indicate that the deterministic Wu+KM and random NG+KM approaches leading to the best quantized images.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mariusz Frackiewicz, Mariusz Frackiewicz, Henryk Palus, Henryk Palus, } "In search of a new initialization of K-means clustering for color quantization", Proc. SPIE 9875, Eighth International Conference on Machine Vision (ICMV 2015), 987506 (8 December 2015); doi: 10.1117/12.2228712; https://doi.org/10.1117/12.2228712
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

Multiresolution training of Kohonen neural networks
Proceedings of SPIE (September 16 2007)
Fractal transform coding of color images
Proceedings of SPIE (September 15 1994)
A universal color image quality metric
Proceedings of SPIE (August 07 2003)
Color image processing for date quality evaluation
Proceedings of SPIE (January 18 2010)

Back to Top