Abstract | ||
---|---|---|
In this paper, a detail-enhancement and super-resolution algorithm based on detail synthesis is proposed. The novelty of this algorithm is in combining local self-similarity search and singular value decomposition of patches together to obtain details with more natural high-frequency. The proposed algorithm improves the facet or line phenomenon on edges and areas that have rich texture. The algorithm firstly searches for an image patch and extracts the high-frequency components based on a local self-similarity of the original, low-resolution image. The matrix of the high-frequency block is then decomposed into two sub-spaces by the singular value decomposition and the pseudo high-frequency is removed by a soft threshold. Then, the high-frequency block is reconstructed using effective singular values. The final super-resolution image is restored by the detail synthesis with the initial super-resolution image. The experimental results show that the proposed method can significantly remove the artificial effect of facet or line phenomenon caused by pseudo high-frequency. Moreover, the method is also applicable to other super-resolution algorithm in detail enhancement. A detail-enhancement and super-resolution algorithm based on detail synthesis is proposed.It combines local self-similarity search and singular value decomposition of patches together.The high-frequency block is reconstructed using effective singular values.It improved the facet or line phenomenon on edges and areas that have rich texture.The method is also applicable to other super-resolution algorithm in detail enhancement. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.image.2016.11.001 | Sig. Proc.: Image Comm. |
Keywords | Field | DocType |
Super resolution,Detail enhancement,Singular value decomposition,Local self-similarity | Computer vision,Singular value decomposition,Singular value,Matrix (mathematics),Computer science,Tensor completion,Artificial intelligence,Facet (geometry),Superresolution | Journal |
Volume | Issue | ISSN |
50 | C | 0923-5965 |
Citations | PageRank | References |
4 | 0.44 | 26 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
jinsheng xiao | 1 | 54 | 7.78 |
Enyu Liu | 2 | 7 | 1.16 |
Ling Zhao | 3 | 4 | 0.44 |
Yuan-Fang Wang | 4 | 835 | 137.72 |
Wenbin Jiang | 5 | 355 | 36.55 |