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) estimat...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.展开更多
Based on the principle of spatial pyramid for signal, a multi-scale transform of two-dimensional （2D） interpolating pyramid is constructed by the nonlinear median operator. The transform properties of error diffuse ...Based on the principle of spatial pyramid for signal, a multi-scale transform of two-dimensional （2D） interpolating pyramid is constructed by the nonlinear median operator. The transform properties of error diffuse halftoning noise on multiple scales are investigated and analyzed through experiments. According to these properties, a robust inverse halftoning method is proposed. The halftoning image is firstly preprocessed by a Gaussian low-pass filter, and decomposed by the one-scale transform. Then a Wiener filter is employed to the detailed coefficients. Finally an inverse image is reconstructed. Experimental results show that the proposed transform has the advantage of separating the halftoning noise and image detail over linear multi-resolution transform. The presented inverse halftoning method performs some excellent abilities on sharp edge, high peak signal-to-noise ratio （PSNR）, and small memory requirement.展开更多
文摘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.
基金This work was supported by the Pre-Research Foundation of Ministries and Commissions(No.51416050205DZ0144)Natural Science Foundation of Shaanxi Province (No.2004F32)the Scientific Research Program from the Education Department of Shaanxi Province (No.04JK244).
文摘Based on the principle of spatial pyramid for signal, a multi-scale transform of two-dimensional （2D） interpolating pyramid is constructed by the nonlinear median operator. The transform properties of error diffuse halftoning noise on multiple scales are investigated and analyzed through experiments. According to these properties, a robust inverse halftoning method is proposed. The halftoning image is firstly preprocessed by a Gaussian low-pass filter, and decomposed by the one-scale transform. Then a Wiener filter is employed to the detailed coefficients. Finally an inverse image is reconstructed. Experimental results show that the proposed transform has the advantage of separating the halftoning noise and image detail over linear multi-resolution transform. The presented inverse halftoning method performs some excellent abilities on sharp edge, high peak signal-to-noise ratio （PSNR）, and small memory requirement.
