On the computational aspects of Gibbs-Markov random field modeling of missing-data in image sequences

Abstract

Abstract-Gibbs-Markov random field (GMRF) modeling has been shown to be a robust method in the detection of missing-data in image sequences for a video restoration application. However, the maximum a posteriori probability (MAP) estimation of the GMRF model requires computationally expensive optimization algorithms in order to achieve an optimal solution. The continuous relaxation labeling (RL) is explored in this paper as an efficient approach for solving the optimization problem. The conversion of the original combinatorial optimization into a continuous RL formulation is presented. The performance of the RL formulation is analyzed and compared with that of other optimization methods such as stochastic simulated annealing, iterated conditional modes, and mean field annealing. The results show that RL holds out promise as an optimization algorithm for problems in image sequence processing.

Detection of dirt impairments from archived film sequences: survey and evaluations

“…The approaches used in our evaluation include SDIp, ROD, SSMF, Finally, results using Markov modelling is also compared and labelled as "MRF" in the evaluations, similar approaches can be found in [24,33,34,36,37,40,56,58]. Consequently, in total nine ROC curves are calculated for each sequence in our evaluation.…”

“…Gibbs-Markov random fields [24], [31][32][33][34][35][36][37]. The determination of a MRF prior allows the detection of dirt in a Bayesian framework [3], [38][39].…”

Segmentation-Assisted Detection of Dirt Impairments in Archived Film Sequences

“…In the framework of motion compensation, model-based approaches can be used, such as Wiener filtering, AR (auto-regressive), MRF (Markov random filed), Gibbs distribution, and Gibbs-Markov random fields [3], [8], [16], [18], [22][23][24][25][26][27]. The determination of a MRF prior allows the detection of dirt in a Bayesian framework [1], [19], [20].…”