This paper presents a ne w wavelet -based image denoising method which is "Bayesian Network" are probably the most popular type of graphical model.In this paper our objective is to construct a Bayesian Network from a single image for denoising purpose.The construction of a Bayesian Network involves prior knowledge of the probability relationships between the variables of interest.Learning approaches are widely used to construct Bayesian Network that best represent the joint probabilities of

more »

... ning data. In this method the data is represented in wavelet domain and restriciting the space of possible networks by using certain techniques.The proposed approach exploits a hidden Bayesian network constructed from wavelet coefficient to model the prior probability of the original image.Then use the belief propagation (BP) algorithm which estimates a coefficient of an image as the maximum-a-posterior (MAP) estimator to derive the denoised wavelet coefficient. We show that if the network is a spanning tree,the standard BP algorithm can perform MAP estimation efficiently.Our experiment results demonstrate that in terms of the peak-signal-to-noise ratio and perceptual quality the reconstructed image has been improved.The planned approach out performs state-of-the-art algorithms on several images mostly in the textured regions, with various amounts of white Gaussian noise.