원문정보
초록
영어
Rician noise pollutes Magnetic Resonance Imaging (MRI) image and makes later work worse. In allusion to remove noise while lessen the loss of details as low as possible, this paper proposed an filter algorithm which comprehensive utilize Genetic Algorithm (GA), PDE and TV, based on 4th order Partial Differential Equations (PDE) and Total Variation (TV) theory. First, it calculates the Total Variation(TV) and the 4th order PDE of kth image, and gives them weight coefficients. Then, it finds the optimal Standard deviation of image of kth image by adjusting weight coefficients based on GA algorithm. Third, it compares PSNR of kth image and PSNR of k+1th image to find whether the algorithm is over. Experimental results show that our new algorithm presented in this paper is more effective in removing Rician noise and giving better Peak Signal Noise Ratio (PSNR) gains without manual intervention in comparison with other traditional filters.
목차
1. Introduction
2. Related Works
2.1. Rician Noise
2.2. Total Variation Minimization (TVM)
2.3. Fourth-order PDEs
3. Proposed Model
3.1. Target Function
3.2. Workflow
4. Experimental Results and Analysis
4.1. Evaluation Index
4.2. Experimental Results
5. Conclusions
Acknowledgments
References