作者: Bin Dong , Ruohan Zhan
DOI:
关键词:
摘要: This paper proposes a spatial-Radon domain CT image reconstruction model based on data-driven tight frames (SRD-DDTF). The proposed SRD-DDTF combines the idea of joint and Radon inpainting \cite{Dong2013X} that for denoising \cite{cai2014data}. It is different from existing models in both its corresponding high quality projection are reconstructed simultaneously using sparsity priors by adaptively learned data to provide optimal sparse approximations. An alternative minimization algorithm designed solve which nonsmooth nonconvex. Convergence analysis provided. Numerical experiments showed superior especially recovering some subtle structures images.