Statistical-Mechanical Analysis of Inverse Digital-Halftoning. Inoue, J., Saika, Y., & Okada, M. In Intelligent Systems Design and Applications, 2007. ISDA 2007. Seventh International Conference on, pages 617 -622, oct., 2007.
doi  abstract   bibtex   
We propose a theoretical framework to investigate statistical performance of inverse digital-halftoning problems. In the context of the maximizer of the posterior marginal (MPM) estimate corresponding to the Markov random fields (MRFs) model in which each pixel takes discrete values such as 1, ..., Q, we formulate the problem of inverse digital-halftoning in which digital images are generated by the threshold constant and the so-called Bayers' matrices. To construct the Gibbs sampler for the MRFs, we carry out Markov chain Monte Carlo (MCMC) simulations and investigate hyper-parameter dependence of the performance in terms of the mean-square error. By using the statistical-mechanical analysis, we also investigate averaged case performance of the inverse-halftoning for the corresponding analytically tractable class of the MRFs models. Both equilibrium and dynamical properties of the MPM estimation of the original grayscale images are revealed.
@inproceedings{4389676,
	Author = {Inoue, J.-i. and Saika, Y. and Okada, M.},
	Booktitle = {Intelligent Systems Design and Applications, 2007. ISDA 2007. Seventh International Conference on},
	Date-Added = {2012-10-22 15:14:10 +0000},
	Date-Modified = {2012-10-22 15:14:10 +0000},
	Doi = {10.1109/ISDA.2007.43},
	Keywords = {Bayers matrices;Gibbs sampler;Markov chain Monte Carlo simulations;Markov random fields model;digital images;grayscale images;hyper-parameter dependence;inverse digital-halftoning problems;inverse-halftoning;mean-square error;posterior marginal estimate;statistical performance;statistical-mechanical analysis;threshold constant;Bayes methods;Markov processes;Monte Carlo methods;image colour analysis;},
	Month = {oct.},
	Pages = {617 -622},
	Title = {Statistical-Mechanical Analysis of Inverse Digital-Halftoning},
	Year = {2007},
	Abstract = {We propose a theoretical framework to investigate statistical performance of inverse digital-halftoning problems. In the context of the maximizer of the posterior marginal (MPM) estimate corresponding to the Markov random fields (MRFs) model in which each pixel takes discrete values such as 1, ..., Q, we formulate the problem of inverse digital-halftoning in which digital images are generated by the threshold constant and the so-called Bayers' matrices. To construct the Gibbs sampler for the MRFs, we carry out Markov chain Monte Carlo (MCMC) simulations and investigate hyper-parameter dependence of the performance in terms of the mean-square error. By using the statistical-mechanical analysis, we also investigate averaged case performance of the inverse-halftoning for the corresponding analytically tractable class of the MRFs models. Both equilibrium and dynamical properties of the MPM estimation of the original grayscale images are revealed.},
	Bdsk-Url-1 = {http://dx.doi.org/10.1109/ISDA.2007.43}}

Downloads: 0