Name
Abstract | ||
|---|---|---|
A number of image super resolution algorithms based on the sparse coding have successfully implemented multi-frame super resolution in recent years. In order to utilize multiple low-resolution observations, both accurate image registration and sparse coding are required. Previous study on multi-frame super resolution based on sparse coding firstly apply block matching for image registration, followed by sparse coding to enhance the image resolution. In this paper, these two problems are solved by optimizing a single objective function. The proposed formulation not only has a mathematically interesting structure, called the double sparsity, but also yields comparable or improved numerical performance to conventional methods. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.neucom.2017.02.043 | Neurocomputing |
Keywords | Field | DocType |
Image Super Resolution,Sparse Coding,Double Sparsity,Dictionary Learning | Computer vision,Dictionary learning,Pattern recognition,Neural coding,Sparse approximation,Artificial intelligence,Single objective,Superresolution,Image resolution,Machine learning,Mathematics,Image registration | Journal |
Volume | Issue | ISSN |
240 | C | 0925-2312 |
Citations | PageRank | References |
5 | 0.41 | 26 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Toshiyuki Kato | 1 | 19 | 2.10 |
| Hideitsu Hino | 2 | 99 | 25.73 |
| Noboru Murata | 3 | 855 | 170.36 |