Optimization of Paintbrush Rendering of Images by Dynamic MCMC Methods
We have developed a new stochastic image rendering method for the compression, description and segmentation of images. This paintbrush-like image transformation is based on a random searching to insert brush-strokes into a generated image at decreasing scale of brush-sizes, without predefined models or interaction. We introduced a sequential multiscale image decomposition method, based on simulated rectangular-shaped paintbrush strokes. The resulting images look like good-quality paintings with well-defined contours, at an acceptable distortion compared to the original image. The image can be described with the parameters of the consecutive paintbrush strokes, resulting in a parameter-series that can be used for compression. The painting process can be applied for image representation, segmentation and contour detection. Our original method is based on stochastic exhaustive searching which takes a long time of convergence. In this paper we propose a modified algorithm of speed up of about 2x where the faster convergence is supported by a dynamic Metropolis Hastings rule.
KeywordsMonte Carlo Markov Chain Exhaustive Search Anisotropic Diffusion Monte Carlo Markov Chain Method Target Density
Unable to display preview. Download preview PDF.
- 1.Y. Fisher. (ed.), Fractal Image Compression, Springer Verlag (1994)Google Scholar
- 4.H. H.S. Ip, H. T. F. Wong, “Generation of Brush Written Characters with fractal Characteristics from True-type Fonts”, ICCPOL, 17th Int. Conf. on Computer Processing of Oriental Languages, pp. 156–161, Hong Kong (1997)Google Scholar
- 5.H. H S Ip, H. T F Wong, “Calligraphic Character Synthesis using Brush Model”, CGI’97, Computer Graphics International conference, pp. 13–21, Hasselt-Diepenbeek, Belgium, June 23–27 (1997)Google Scholar
- 6.T. Lindeberg, B. M. Haar Romeny, “Linear scale-space I-II”, Geometry-Driven Diff. In Computer Vision, Kluwer Academic Publishers, pp. 1–72 (1992)Google Scholar
- 7.P. Litwinowicz, ‘Processing Images and Video for An Impressionist Effect’, Computer Graphics, (Proc.SIGGRAPH’1997), pp. 407–414 (1997)Google Scholar
- 8.R. Neff, A. Zakhor, “Very low bit-rate video coding based on matching pursuits”, IEEE Tr. CAS VT, Vol. 7, pp. 158–171 (1997)Google Scholar
- 9.Ch. P. Robert, G. Casella, “Monte Carlo Statistical Methods“, Springer Text in Statistics (1999)Google Scholar
- 10.T. Szirányi, I. Kopilovic, B. P. Tóth, “Anisotropic Diffusion as a Preprocessing Step for Efficient Image Compression”, Proc. of the 14 th ICPR Brisbane, IAPR&IEEE, Australia, pp. 1565–1567, August 16–20 (1998)Google Scholar
- 11.T. Szirányi, Z. Toth, “Random Paintbrush Transformation”, 15 th ICPR, Barcelona, IAPR&IEEE, V. 3, pp. 155–158 (2000)Google Scholar
- 12.T. Szirányi, J. Zerubia, “Markov Random Field Image Segmentation using Cellular Neural Network”, IEEE CAS I., Vol. 44, pp. 86–89 (1997)Google Scholar
- 13.P. Teo, D. Heeger, “Perceptual Image Distortion”, First IEEE Int.Conf. Image Proc., Vol. 2, pp. 982–986 (1994)Google Scholar
- 14.S.C. Zhu, D. Mumford, “Prior Learning and Gibbs Reaction-Diffusion“, IEEE Tr. PAMI, Vol. 19, pp. 1236–1250 (1997)Google Scholar