Abstract
It has been demonstrated that the sparse representation based framework is one of the most popular and promising ways to handle the single image super-resolution (SISR) issue. However, due to the complexity of image degradation and inevitable existence of noise, the coding coefficients produced by imposing sparse prior only are not precise enough for faithful reconstructions. In order to overcome it, we present an improved SISR reconstruction method based on the proposed bidirectionally aligned sparse representation (BASR) model. In our model, the bidirectional similarities are first modeled and constructed to form a complementary pair of regularization terms. The raw sparse coefficients are additionally aligned to this pair of standards to restrain sparse coding noise and therefore result in better recoveries. On the basis of fast iterative shrinkage-thresholding algorithm, a well-designed mathematic implementation is introduced for solving the proposed BASR model efficiently. Thorough experimental results indicate that the proposed method performs effectively and efficiently, and outperforms many recently published baselines in terms of both objective evaluation and visual fidelity.
Similar content being viewed by others
Notes
This whole operation can be directly accomplished by using the MATLAB function “imresize” with the method option “bicubic”.
References
Aguena ML, Mascarenhas ND (2006) Multispectral image data fusion using POCS and super-resolution. Comput Vis Image Underst 102(2):178–187
Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imag Sci 2(1):183–202
Bioucas-Dias JM, Figueiredo MAT (2007) A new TwIST: two-step iterative shrinkage/thresholding algorithms for image restoration. IEEE Trans Image Process 16(12):2992–3004
Bose NK, Kim HC, Valenzuela HM (1993) Recursive implementation of total least squares algorithm for image reconstruction from noisy, undersampled multiframes. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 269–272
Buades A, Coll B, Morel J (2005) A non-local algorithm for image denoising. In: IEEE computer society conference on Computer Vision and Pattern Recognition (CVPR), 60–65
Candè EJ, Wakin MB (2008) An introduction to compressive sampling. IEEE Signal Process Mag 25(2):21–30
Candes EJ, Romberg JK, Tao T (2006) Stable signal recovery from incomplete and inaccurate measurements. Commun Pure Appl Math 59(8):1207–1223
Candes EJ, Wakin MB, Boyd SP (2008) Enhancing sparsity by reweighted ℓ 1 minimization. J Fourier Anal Appl 14(5–6):877–905
Chang H, Yeung DY, Xiong Y (2004) Super-resolution through neighbor embedding. In: IEEE computer society conference on Computer Vision and Pattern Recognition (CVPR), I-I
Daubechies I, Defrise M, De Mol C (2004) An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun Pure Appl Math 57(11):1413–1457
Dong W, Zhang L, Shi G, Wu X (2011) Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans Image Process 20(7):1838–1857
Dong W, Zhang L, Shi G (2011) Centralized sparse representation for image restoration. In: IEEE International Conference on Computer Vision (ICCV), 1259–1266
Dong W, Zhang L, Shi G, Li X (2013) Nonlocally centralized sparse representation for image restoration. IEEE Trans Image Process 22(4):1620–1630
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Donoho DL (2006) For most large underdetermined Systems of Linear Equations the minimal 1-norm solution is also the sparsest solution. Commun Pure Appl Math 59(6):797–829
Elad M, Aharon M (2006) Image Denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15(12):3736–3745
Elad M, Feuer A (1997) Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images. IEEE Trans Image Process 6(12):1646–1658
Elad M, Yavneh I (2009) A plurality of sparse representations is better than the sparsest one alone. IEEE Trans Inf Theory 55(10):4701–4714
Farsiu S, Robinson MD, Elad M, Milanfar P (2004) Fast and robust multiframe super resolution. IEEE Trans Image Process 13(10):1327–1344
Farsiu S, Robinson D, Elad M, Milanfar P (2004) Advances and challenges in super-resolution. Int J Imaging Syst Technol 14(2):47–57
Freeman WT, Jones TR, Pasztor EC (2002) Example-based super-resolution. IEEE Comput Graph Appl 22(2):56–65
He Y, Yap K, Chen L, Chau L (2009) A soft MAP framework for blind super-resolution image reconstruction. Image Vis Comput 27(4):364–373
Kim SP, Su W (1993) Recursive high-resolution reconstruction of blurred multiframe images. IEEE Trans Image Process 2(4):534–539
Kim SP, Bose NK, Valenzuela HM (1990) Recursive reconstruction of high resolution image from noisy undersampled multiframes. IEEE Trans Acoust Speech Signal Process 38(6):1013–1027
Li X, Hu Y, Gao X, Tao D, Ning B (2010) A multi-frame image super-resolution method. Signal Process 90(2):405–414
Lin ZC, Shum HY (2004) Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Trans Pattern Anal Mach Intell 26(1):83–97
Lu X, Yuan H, Yan P, Yuan Y, Li X (2012) Geometry constrained sparse coding for single image super-resolution. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR), 1648–1655
Mishra D, Majhi B, Sa PK, Dash R (2016) Development of robust neighbor embedding based super-resolution scheme. Neurocomputing 202:49–66
Nasrollahi K, Moeslund TB (2014) Super-resolution: a comprehensive survey. Mach Vis Appl 25(6):1423–1468
Nguyen N, Milanfar P, Golub G (2001) A computationally efficient superresolution image reconstruction algorithm. IEEE Trans Image Process 10(4):573–583
Omer OA, Tanaka T (2011) Region-based weighted-norm with adaptive regularization for resolution enhancement. Digital Signal Process 21(4):508–516
Park SC, Park MK, Kang MG (2003) Super-resolution image reconstruction: a technical overview. IEEE Signal Process Mag 20(3):21–36
Peleg T, Elad M (2014) A statistical prediction model based on sparse representations for single image super-resolution. IEEE Trans Image Process 23(6):2569–2582
Purkait P, Pal NR, Chanda B (2014) A fuzzy-rule-based approach for single frame super resolution. IEEE Trans Image Process 23(5):2277–2290
Qin F, He X, Chen W, Yang X, Wu W (2009) Video superresolution reconstruction based on subpixel registration and iterative back projection. J Electron Imaging 18(1):13007
Stark H, Oskoui P (1989) High-resolution image recovery from image-plane arrays, using convex projections. J Opt Soc Am A 6(11):1715–1726
Tian J, Ma K (2011) A survey on super-resolution imaging. SIViP 5(3):329–342
Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. In: IEEE International Conference on Computer Vision (ICCV), 1920–1927
Timofte R, De Smet V, Van Gool L (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Asian Conference on Computer Vision (ACCV), 111–126
Timofte R, Rothe R, Van Gool L (2016) Seven ways to improve example-based single image super resolution. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR), 1865–1873
Tsai RY, Huang TS (1984) Multiframe image restoration and registration. Advances in computer vision and Image Processing 1(2):317–339
Vrigkas M, Nikou C, Kondi LP (2013) Accurate image registration for MAP image super-resolution. Signal Process Image Commun 28(5):494–508
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Yan C, Zhang Y, Dai F, Wang X, Li L, Dai Q (2014) Parallel deblocking filter for HEVC on many-core processor. Electron Lett 50(5):367–368
Yan C, Zhang Y, Dai F, Zhang J, Li L, Dai Q (2014) Efficient parallel HEVC intra-prediction on many-core processor. Electron Lett 50(11):805–806
Yan C, Zhang Y, Xu J, Dai F, Li L, Dai Q, Wu F (2014) A highly parallel framework for HEVC coding unit partitioning tree decision on many-core processors. IEEE Signal Process Lett 21(5):573–576
Yan C, Zhang Y, Xu J, Dai F, Zhang J, Dai Q, Wu F (2014) Efficient parallel framework for HEVC motion estimation on many-core processors. IEEE Trans Circuits Syst Video Technol 24(12):2077–2089
Yang J, Wright J, Huang T, Ma Y (2008) Image super-resolution as sparse representation of raw image patches. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR), 1–8
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Yang S, Liu Z, Wang M, Sun F, Jiao L (2011) Multitask dictionary learning and sparse representation based single-image super-resolution reconstruction. Neurocomputing 74(17):3193–3203
Yue L, Shen H, Yuan Q, Zhang L (2014) A locally adaptive L1− L2 norm for multi-frame super-resolution of images with mixed noise and outliers. Signal Process 105:156–174
Zeng W, Lu X (2012) A generalized DAMRF image modeling for superresolution of license plates. IEEE Trans Intell Transp Syst 13(2):828–837
Zeng W, Lu X, Fei S (2015) Image super-resolution employing a spatial adaptive prior model. Neurocomputing 162:218–233
Zeyde R, Elad M, Protter M (2012) On single image scale-up using sparse-representations. Curves and Surfaces (Springer), 711–730.
Zhang X, Wu X (2008) Image interpolation by adaptive 2-D autoregressive modeling and soft-decision estimation. IEEE Trans Image Process 17(6):887–896
Zhang X, Feng X, Wang W (2013) Two-direction nonlocal model for image Denoising. IEEE Trans Image Process 22(1):408–412
Zhou L, Lu X, Yang L (2014) A local structure adaptive super-resolution reconstruction method based on BTV regularization. Multimedia Tools and Applications 71(3):1879–1892
Acknowledgments
The authors would like to thank the associate editor and anonymous reviewers for their constructive and precious comments, which helped us a lot in improving the presentation of this work.
This work was supported by the National Natural Science Foundation of China (No.61374194, No.61403081), the National Key Science & Technology Pillar Program of China (No.2014BAG01B03), the Key Research and Development Program of Jiangsu Province (No. BE2016739), and a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Appendix A: Solving BASR on the basis of FISTA
Appendix A: Solving BASR on the basis of FISTA
Here, we provide the main process for solving the proposed BASR model (11) on the basis of FISTA [3] which is an effective algorithm for linear inverse problems with dense matrix data. Even though this part is more detailed when compared with that in subsection 3.4, it is still a sketch only. For comprehensive details, we direct you to [3, 11].
First of all, for the sake of convenience, let us divide (11) into two functions and define them respectively
Then, according to the mathematic results derived in [3], model (11) can be approximated by considering the following formula at the given point \( {\boldsymbol{\alpha}}_i^{(l)} \)(i.e., the sparse coefficient in the l-th iteration)
It has been proved that the above formula admits a unique minimizer. By getting rid of the constant terms, function ρ can be reformulated into a briefer from
Notation L here is involved to control the magnitude of step-size. After taking the derivative of (15) with respect to \( {\boldsymbol{\alpha}}_i^{\left( l+1\right)} \) and making it equal to zero, we can get
If we let the left side part of (16) form anther new function F, that is
Then, the function ρ can be expressed as the inverse function of F
And it can be readily formulated as
It can be noted that the above algorithm corresponds to the general process of classic iterative thresholding algorithm (ITA) [11], which can be viewed as an extension of the classic gradient-based method. Function ρ acts as the shrinkage operator and processed in a pixelwise manner. Although it is well known that the first order optimization algorithms are often the only simple and practical option to deal with large-scale problems such as the case in this paper, it still has been found that the sequence produced by the above algorithm converges quite slowly to the final minimizer [4]. To accelerate the algorithm, the temporary variable before shrinkage operation in (18) ought not to be computed by considering the result obtained in the previous iteration only, but rather to be calculated by utilizing a very special linear combination of the previous two results. Therefore, formula (18) can be modified as follows:
Besides, anther condition ensuring convergence is to require that the step-size controller L is set to be no less than the smallest Lipschitz constant of the gradient of function f, and this quantity can be determined by employing a backtracking step-size rule. In summary, a step-by-step description of the above implementation can be given in Algorithm 1.
Rights and permissions
About this article
Cite this article
Xie, C., Zeng, W., Jiang, S. et al. Bidirectionally aligned sparse representation for single image super-resolution. Multimed Tools Appl 77, 7883–7907 (2018). https://doi.org/10.1007/s11042-017-4689-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4689-7