Texture synthesis via a noncausal nonparametric multiscale Markov random field
- 1 June 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 7 (6) , 925-931
- https://doi.org/10.1109/83.679446
Abstract
Our noncausal, nonparametric, multiscale, Markov random field (MRF) model is capable of synthesizing and capturing the characteristics of a wide variety of textures, from the highly structured to the stochastic. We use a multiscale synthesis algorithm incorporating local annealing to obtain larger realizations of texture visually indistinguishable from the training texture.Keywords
This publication has 12 references indexed in Scilit:
- Near-Regular Texture SynthesisPublished by Springer Nature ,2009
- Robust method for texture synthesis-by-analysis based on a multiscale Gabor schemePublished by SPIE-Intl Soc Optical Eng ,1996
- TEXTURE ANALYSISPublished by World Scientific Pub Co Pte Ltd ,1993
- Multiple resolution segmentation of textured imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Random fields and inverse problems in imagingPublished by Springer Nature ,1990
- A renormalization group approach to image processing problemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A parallel image segmentation algorithm using relaxation with varying neighborhoods and its mapping to array processorsComputer Vision, Graphics, and Image Processing, 1987
- Image Analysis Using Multigrid Relaxation MethodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Textons, the elements of texture perception, and their interactionsNature, 1981