A Non-Local Algorithm for Image Denoising
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Nonlocal Prior Bayesian Tomographic Reconstruction
Journal of Mathematical Imaging and Vision
Limited view CT reconstruction and segmentation via constrained metric labeling
Computer Vision and Image Understanding
Necessary and sufficient convergence conditions for algebraic image reconstruction algorithms
IEEE Transactions on Image Processing
Iterative weighted maximum likelihood denoising with probabilistic patch-based weights
IEEE Transactions on Image Processing
Generalized Gibbs priors based positron emission tomography reconstruction
Computers in Biology and Medicine
Nonparametric optimization of constrained total variation for tomography reconstruction
Computers in Biology and Medicine
Hi-index | 0.00 |
In divergent-beam computed tomography (CT), sparse angular sampling frequently leads to conspicuous streak artifacts. In this paper, we propose a novel non-local means (NL-means) based iterative-correction projection onto convex sets (POCS) algorithm, named as NLMIC-POCS, for effective and robust sparse angular CT reconstruction. The motivation for using NLMIC-POCS is that NL-means filtered image can produce an acceptable priori solution for sequential POCS iterative reconstruction. The NLMIC-POCS algorithm has been tested on simulated and real phantom data. The experimental results show that the presented NLMIC-POCS algorithm can significantly improve the image quality of the sparse angular CT reconstruction in suppressing streak artifacts and preserving the edges of the image.