Implementation, modeling, for deduction in the fields of random Markov algorithm for noise reduction of image using ICM

Removing noise from images is still a major challenge for engineers. Several different noise reduction algorithms have been proposed, each with advantages and disadvantages. The Markov algorithm is a n-dimensional random variable defined in the network separately. In particular, each node in the graph represents a random variable, and branches (arcs) represent probabilistic dependencies between variables. These conditional dependencies are often evaluated by specific statistical and probabilistic methods. Bias networks combine the principles of graph theory, probability theory, computer science, and statistics. One of the issues that focuses its attention on processing image signals is signal modeling. There are various choices for modeling images and features. From the standpoint of noise elimination models, these are categorized into two categories of specific models and statistical models. A randomized Markov algorithm is one of the theories that is used for probability. In this paper, we present relatively new ideas for eliminating noise from images. It is also a method for eliminating noise from an image using the ICM model (conditional state effect), which is a model of a randomized Markov algorithm. Generally, graphic models with non-directional branches are called random Markov fields or Markov networks. These networks provide a simple definition of the independence of variables based on the concept of the Markov layer. Markov networks are very famous in the fields of statistical physics and computer vision.

کلیدواژه ها:

Noise removal from image ، Markov model ، Conditional state