An iterative Gibbsian technique for reconstruction of m-ary images

The reconstruction of m-ary images corrupted by independent noise is treated. The original image is modeled by a Markov Random Field (MRF) whose parameters are unknown. Likewise, the probabilistic structure of the noise is unknown. This paper presents an iterative procedure which performs the parameter estimation and image reconstruction tasks at the same time. The procedure that we call Gibbsian EM algorithm, is a generalization to the MRF context of a general algorithm, known as the EM algorithm, used to approximate maximum-likelihood estimates for incomplete data problems. A number of experiments are presented in the case of Gaussian noise and binary noise, showing that the Gibbsian EM algorithm is useful and effective for image reconstruction and segmentation.