Single Image Super-Resolution Reconstruction Technique based on A Single Hybrid Dictionary
Pages 14759 - 14779
Abstract
A new sparse domain approach is proposed in this paper to realize the single image super-resolution (SR) reconstruction based upon one single hybrid dictionary, which is deduced from the mixture of both the high resolution (HR) image patch samples and the low resolution (LR) ones. Moreover, a linear model is proposed to characterize the relationship between the sparse representations of both the HR image patches and the corresponding LR ones over the same hybrid dictionary. It is shown that, the requirement on the identical sparse representation of both HR and LR image patches over the corresponding HR dictionary and the LR dictionary can be relaxed. It is unveiled that, the use of one single hybrid dictionary can not only provide a more flexible framework to keep the similar sparse characteristics between the HR patches and the corresponding degenerated LR patches, but also to accommodate their differences. On this basis, the sparse domain based SR reconstruction problem is reformulated. Moreover, the proposed linear model between the sparse representations of both the HR patch and the corresponding LR patch over the same hybrid dictionary offers us a new method to interpret the image degeneration characteristics in sparse domain. Finally, practical experimental results are presented to test and verify the proposed SR approach.
References
[1]
Candes EJ, Donoho DL (2000) Curvelets--a surprisingly effective nonadaptive representation for objects with edges, in Curve and Surface Fitting. Vanderbilt Univ. Press
[2]
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proc. IEEE CCVPC 1:275---282
[3]
Donoho DL (2006a) For most large underdetermined systems of linear equations, the minimal ℓ1-norm solution is also the sparsest solution. Commun Pure Appl Math 59:797---829
[4]
Donoho DL (2006b) For most large underdetermined systems of linear equations, the minimal ℓ1-norm near-solution approximates the sparsest near-solution. Commun Pure Appl Math 59:907---934
[5]
Efron B, Hastie T, Johnstone I (2004) Least angle regression. Ann Statist 32:407---499
[6]
Elad M (2010) Sparse and redundant representations, Springer. The Technion - Israel Institute of Technology Haifa, Israel
[7]
Gowreesunker BV, Tewfik AH (2010) Learning sparse representation using iterative subspace identification. IEEE Trans Signal Process 58:3055---3065
[8]
Jia K, Wang X, Tang X (2013) Image transformation based on learning dictionaries across image spaces. IEEE Trans Pattern Anal Mach Intell 35:367---380
[9]
Jing G, Shi Y, Kong D, Ding W, Yin B (2014) Image super-resolution based on multi-space sparse representation. Multimedia Tools Appl 70:741---755
[10]
Lewicki MS, Sejnowski TJ (2000) Learning overcomplete representations. Neural Comput 12:337---365
[11]
Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10:1521---1527
[12]
Moustafa M, Ebeid HM, Helmy A, Nazamy TM (2015) Super-resolution: sparse dictionary design method using quantitative comparison. In: Proc IEEE ICICIS 2015:12---14
[13]
Murray JF, Kreutz-Delgado K (2007) Learning sparse overcomplete codes for images. J VLSI Sig Proc Syst 45:97---110
[14]
Na A, Peng J, Zhu X, Feng X (2016) Single image super-resolution by combining self-learning and example-based learning methods. Multimedia Tools Appl 75:6647---6662
[15]
Olshausen BA, Field DJ (1997) Sparse coding with an overcomplete basis set: a strategy employed by v1? Vis Res 37:3311---3325
[16]
Peleg T, Elad M (2014) A statistical prediction model based on sparse representations for single image super-resolution. IEEE Trans Image Process 23:2569---2582
[17]
Pennec EL, Mallat S (2005) Sparse geometric image representations with bandelets. IEEE Trans Image Process 14:423---438
[18]
Shaker GM, EL-Fattah AA, Dessouky MI, Nahas MYE (2013) Super resolution using dictionary technique, in Proc. NRSC 306-318
[19]
Sun Y, Gu G, Sui X, Liu Y (2016) Compressive super-resolution imaging based on local and nonlocal regularizations. IEEE Photonics Journal 8:1---12
[20]
Tropp J, Gilbert AC, Kriahnaprasad PS (2007) Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inf Theory 53:4655---4666
[21]
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600---612
[22]
Wang S, Zhang L, Liang Y, Pan Q (2012) Semi-Coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In: Proc comput. Soc conf Vis Pattern Recogn 157:2216---2223
[23]
Yang J, Wright J, Huang T, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19:2861---2873
[24]
Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super-resolution. IEEE Trans Image Process 21:3467---3478
[25]
Yang J, Zhang X, Peng W, Liu Z (2015) A novel regularized K-SVD dictionary learning based medical image super-resolution algorithm. Multimedia Tools Appl 75:13107---13120
[26]
Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15:2226---2238
[27]
Zhang K, Gao X, Tao D, Li X (2012) Multi-scale dictionary for single image super-resolution. In: Proc IEEE comput Soc conf Vis Pattern Recogn 157:1114---1121
- Single Image Super-Resolution Reconstruction Technique based on A Single Hybrid Dictionary
Recommendations
Fast Learning-Based Single Image Super-Resolution
We present a learning-based single image super-resolution (SISR) method to obtain a high resolution (HR) image from a single given low resolution (LR) image. Our method gives more accurate results while also testing (runs) and training faster with a ...
Adaptive regularised l2‐boosting on clustered sparse coefficients for single image super‐resolution
In this study, the authors propose a novel approach for single image super‐resolution. Their method is based on the idea of learning a mapping function, which can reveal the intrinsic relationship between sparse coefficients of low‐resolution (LR) and ...
Single image super resolution based on sparse domain selection
Single image super-resolution (SR) aims to form a high-resolution (HR) image from an input low-resolution (LR) image. The sparse coding-based example learning methods typically assume that the low-resolution and high-resolution features share the same ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © Copyright © 2017 Springer Science+Business Media New York.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 01 July 2017
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in