Digital Image Enhancement and Noise Filtering by Use of Local Statistics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Kalman filtering in two dimensions
IEEE Transactions on Information Theory
Bayes Smoothing Algorithms for Segmentation of Binary Images Modeled by Markov Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image denoising with complex ridgelets
Pattern Recognition
Hi-index | 0.00 |
The main theme of this paper is the derivation of a new algorithm for restoring digitized images degraded by both additive and multiplicative noise sources. In order to keep the derivation sufficiently general, the authors also include degradation caused by blur and a class of nonlinearities. The images under consideration are modeled as Markov random fields, while the additive and multiplicative noise sources are assumed to be Gaussian processes with known means and variances. Blurring of images is accomplished by a shift-invariant point-spread function. Test results with degraded images indicate that the algorithm is effective in restoring images degraded by high levels of additive and multiplicative noise.