Adaptive quantization and filtering using Gauss-Markov measure field models

We present a new class of models, derived from classical Markov Random Fields, that may be used for the solution of ill-posed problems in image processing and computational vision. They lead to reconstrucion algorithms that are flexible, computationally efficient and biologically plausible. To illustrate their use, we present their application to the reconstruction of the dominant orientation field and to the adaptive quantization and filtering of images in a variety of situations.