Abstract | ||
---|---|---|
The diagnostic medical imaging has provided enormous benefits in the early detection as well as the potential side effect of radiation induced genetic diseases. The super-resolution analysis is proved to be a critical way to maintain the reduction of the radiation dose and the imaging quality. Due to compressive sensing wide research, sparse representation was well applied in super-resolution. It has been widely acknowledged that learning-based super-resolution (SR) methods are effective to generate a high-resolution (HR) image from a single low-resolution (LR) input. This paper presents a new approach to single-image super resolution in the X-Ray photography field: 1) A novel dictionary learning method for enhancing the similarity of the sparse representations between the LR and the HR block pairs through simultaneous training two dictionaries using the theory of PCA is proposed. 2) For each given input LR patch, to find the most proper sub-dictionary in the low-resolution dictionary. 3) Get the corresponding high-resolution sub-dictionary and to solve the ill-posed super-resolution problem by the iterative algorithm and to generate the HR blocks. Comprehensive evaluations are implemented to demonstrate that the proposed methods can definitely improve the performance of the reconstruction in our selected cases. However, there is no proof that this is true for all kinds of structures. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/s11265-016-1163-0 | Signal Processing Systems |
Keywords | Field | DocType |
Dictionary learning,Compressive sensing,Super resolution,Medical imaging | Dictionary learning,K-SVD,Iterative method,Medical imaging,Computer science,Sparse approximation,Algorithm,Photography,Artificial intelligence,Superresolution,Compressed sensing,Machine learning | Journal |
Volume | Issue | ISSN |
88 | 3 | 1939-8018 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
5 |