Multiplicative Noise Removal Using TVL1 Norm and Adaptive Penalty Parameter
Guodong Wang · Journal of Information and Computational Science · 2014
Multiplicative noise removal technology is very useful in many applications. In this paper, we propose a new multiplicative noise removal algorithm using TVL1 norm and adaptive penalty parameter. We use TVL1 norm as the data term and we incorporate the modified total variation regularization term in the objective function to deal with multiplicative noise. The balance of fidelity term and regularization term can be changed in different areas with different gray value. We modify the penalty parameter using facet model and we call it as adaptive penalty parameter. Thus in iterating procedure, our method can change the degree of noise removal in different areas with different noise level adaptively. The results show the outperforming effect of our method.