Image Denoising Method Based On Adaptive Generalized Total Variation

In the acquisition process of various imaging systems,images are inevitably interfered by noise.Therefore,image denoising is a basic and important problem in image processing.At present,image denoising is widely used and plays a key role in astronomy,medicine,aerospace and other fields.In this paper,image denoising algorithms based on adaptive total generalized variation are studied.The main research contents and innovations are as follows:(1)Aiming at speckle noise in ultrasound medical images,and combining the data fidelity term in SO model and the Total Generalized Variation(TGV)regularization term,we propose an adaptive TGV model for the speckle noise removal by using the GCV technology.(2)The existence and uniqueness of the weak solution to the proposed model are proved by using the direct variational method.Then,we develop a fast algorithm for solving numerically the model by incorporating the alternating minimization and GCV methods.Furthermore,numerical experimental results are reported to show the effectiveness and feasibility of the algorithm.(3)Aiming at the Poisson noise in medical and astronomical images,we propose an adaptive TGV algorithm for Poisson noise removal.Numerical experimental results are given to demonstrate that the proposed algorithm not only can remove the Poisson noise effectively,but also recover the texture,structural edge and other details in the observed images.