Image Super Resolution Using Fractal Coding and Residual Network
Fractal coding techniques are an effective tool for describing image textures. Considering the shortcomings of the existing image super-resolution (SR) method, the large-scale factor reconstruction performance is poor and the texture details are incomplete. In this paper, we propose an SR method bas...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2019/9419107 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766280787132416 |
|---|---|
| author | Zhen Hua Haicheng Zhang Jinjiang Li |
| author_facet | Zhen Hua Haicheng Zhang Jinjiang Li |
| author_sort | Zhen Hua |
| collection | DOAJ |
| description | Fractal coding techniques are an effective tool for describing image textures. Considering the shortcomings of the existing image super-resolution (SR) method, the large-scale factor reconstruction performance is poor and the texture details are incomplete. In this paper, we propose an SR method based on error compensation and fractal coding. First, quadtree coding is performed on the image, and the similarity between the range block and the domain block is established to determine the fractal code. Then, through this similarity relationship, the attractor is reconstructed by super-resolution fractal decoding to obtain an interpolated image. Finally, the fractal error of the fractal code is estimated by the depth residual network, and the estimated version of the error image is added as an error compensation term to the interpolation image to obtain the final reconstructed image. The network structure is jointly trained by a deep network and a shallow network. Residual learning is introduced to greatly improve the convergence speed and reconstruction accuracy of the network. Experiments with other state-of-the-art methods on the benchmark datasets Set5, Set14, B100, and Urban100 show that our algorithm achieves competitive performance quantitatively and qualitatively, with subtle edges and vivid textures. Large-scale factor images can also be reconstructed better. |
| format | Article |
| id | doaj-art-bb66de4e0e174d41af98b1b2e2ebd2eb |
| institution | DOAJ |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-bb66de4e0e174d41af98b1b2e2ebd2eb2025-08-20T03:04:38ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/94191079419107Image Super Resolution Using Fractal Coding and Residual NetworkZhen Hua0Haicheng Zhang1Jinjiang Li2School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, 264005, ChinaCo-innovation Center of Shandong Colleges and Universities: Future Intelligent Computing, Shandong Technology and Business University, Yantai, 264005, ChinaCo-innovation Center of Shandong Colleges and Universities: Future Intelligent Computing, Shandong Technology and Business University, Yantai, 264005, ChinaFractal coding techniques are an effective tool for describing image textures. Considering the shortcomings of the existing image super-resolution (SR) method, the large-scale factor reconstruction performance is poor and the texture details are incomplete. In this paper, we propose an SR method based on error compensation and fractal coding. First, quadtree coding is performed on the image, and the similarity between the range block and the domain block is established to determine the fractal code. Then, through this similarity relationship, the attractor is reconstructed by super-resolution fractal decoding to obtain an interpolated image. Finally, the fractal error of the fractal code is estimated by the depth residual network, and the estimated version of the error image is added as an error compensation term to the interpolation image to obtain the final reconstructed image. The network structure is jointly trained by a deep network and a shallow network. Residual learning is introduced to greatly improve the convergence speed and reconstruction accuracy of the network. Experiments with other state-of-the-art methods on the benchmark datasets Set5, Set14, B100, and Urban100 show that our algorithm achieves competitive performance quantitatively and qualitatively, with subtle edges and vivid textures. Large-scale factor images can also be reconstructed better.http://dx.doi.org/10.1155/2019/9419107 |
| spellingShingle | Zhen Hua Haicheng Zhang Jinjiang Li Image Super Resolution Using Fractal Coding and Residual Network Complexity |
| title | Image Super Resolution Using Fractal Coding and Residual Network |
| title_full | Image Super Resolution Using Fractal Coding and Residual Network |
| title_fullStr | Image Super Resolution Using Fractal Coding and Residual Network |
| title_full_unstemmed | Image Super Resolution Using Fractal Coding and Residual Network |
| title_short | Image Super Resolution Using Fractal Coding and Residual Network |
| title_sort | image super resolution using fractal coding and residual network |
| url | http://dx.doi.org/10.1155/2019/9419107 |
| work_keys_str_mv | AT zhenhua imagesuperresolutionusingfractalcodingandresidualnetwork AT haichengzhang imagesuperresolutionusingfractalcodingandresidualnetwork AT jinjiangli imagesuperresolutionusingfractalcodingandresidualnetwork |