[1]SAIKA Yohei,AOKI Toshizumi.Thermodynamicsinspired inverse halftoning via multiple halftone images[J].CAAI Transactions on Intelligent Systems,2012,7(1):86-94.
Copy

Thermodynamicsinspired inverse halftoning via multiple halftone images

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 7 Number of periods: 2012 1 Page number: 86-94 Column: 学术论文—人工智能基础 Public date: 2012-02-25
Title:
Thermodynamicsinspired inverse halftoning via multiple halftone images
Author(s):
SAIKA Yohei1;  AOKI Toshizumi2
1. Department of Information and Computer Engineering, Gunma National College of Technology, 580 Toriba, Maebashi, 3718530, Japan;
2. Department of Natural Science, Gunma National College of Technology, 580 Toriba, Maebashi, 3718530, Japan
Keywords:
inverse halftoning;  statistical mechanics;  Monte Carlo simulation;  Bethe approximation; 
CLC:
TP39
DOI:
-
Abstract:
Based on an analogy between thermodynamics and Bayesian inference, inverse halftoning was formulated using multiple halftone images based on Bayesian inference using the maximizer of the posterior marginal (MPM) estimate. Applying Monte Carlo simulation to a set of snapshots of the QIsing model, it was demonstrated that optimal performance is achieved around the Bayesoptimal condition within statistical uncertainty and that the performance of the Bayesoptimal solution is superior to that of the maximumaposteriori(MAP) estimation which is a deterministic limit of the MPM estimate. These properties were qualitatively confirmed by the meanfield theory using an infiniterange model established in statistical mechanics. Additionally, a practical and useful method was constructed using the statistical mechanical iterative method via the Bethe approximation. Numerical simulations for a 256grayscale standard image show that Bethe approximation works as good as the MPM estimation if the parameters are set appropriately. 
References:
［1］BESAG J. On the statistical analysis of dirty pictures［J］. Journal of the Royal Statistical Society—Series B: Statistical Methodological, 1986, 48(3): 259302.
［2］GONZALES R C, WOODS R C. Digital image processing［M］. Reading, USA: Addison Wiley, 1986.
［3］WINKLER G. Image analysis, random fields and dynamic Monte Carlo methods: a mathematical introduction［M］. Berlin, Germany: SpringerVerlag, 1995.
［4］NISHIMORI H. Statistical physics of spin glasses and information processing: an introduction［M］. Oxford, UK: Oxford Press, 2001.
［5］TANAKA K. Statisticalmechanical approach to image processing［J］. Journal of Physics A: Mathematical and General, 2002, 35(37): R31R150.
［6］ULICHNEY R. Digital halftoning［M］. Cambridge, USA: The MIT Press, 1987.
［7］BAYER B E. An optimum method for twolevel rendition of continuous tone pictures［C］//IEEE International Conference on Communications. New York, USA: IEEE Press, 1973: 1115.
［8］MICELI C M, PARKER K J. Inverse halftoning［J］. Journal of Electronic Imaging, 1992, 1(2): 143151. 
［9］WONG P W. Inverse halftoning and kernel estimation for error diffusion［J］. IEEE Transactions on Image Processing, 1995, 4(4): 486498.
［10］STEVENSON R L. Inverse halftoning via MAP estimation［J］. IEEE Transactions on Image Processing, 1997, 6(4): 574583. 
［11］SAIKA Y, INOUE J, TANAKA H, et al. Bayesoptimal solution to inverse halftoning based on statistical mechanics of the QIsing model［J］. Central European Journal of Physics, 2009, 7(3): 444456.
［12］TIPPING M E, BISHOP C M. Bayesian image superresolution［M］//BECKER S, THRUN S, OBERMAYER K. Advances in Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2003: 12791286.
［13］KANEMURA A, MAEDA S, ISHII S. Superresolution with compound Markov random fields via the variational EM algorithm［J］. Neural Networks, 2009, 22(7): 10251034.
［14］DEMPSTER A P, LAIRD N M, RUBIN D B. Maximumlikelihood from incomplete data via the EM algorithm［J］. Journal of the Royal Statistical Society—Series B: Statistical Methodological, 1977, 39(1): 138.
［15］TANAKA K, INOUE J, TITTERINGTON D M. Probabilistic image processing by means of the Bethe approximation for the QIsing model［J］. Journal of Physics A: Mathematical and General, 2003, 36(43): 1102311035. 
Similar References:

Memo

-

Last Update: 2012-05-07

Copyright © CAAI Transactions on Intelligent Systems