Single-image super-resolution in RGB space via group sparse representation

Super-resolution (SR) is the problem of generating a high-resolution (HR) image from one or more low-resolution (LR) images. This study presents a new approach to single-image super-resolution based on group sparse representation. Two dictionaries are constructed corresponding to the LR and HR image patches, respectively. The sparse coefficients of an input LR image patch in terms of the LR dictionary are used to recover the HR patch from the HR dictionary. When constructing the dictionaries, the three colour channels in a training image patch are considered a group composed of three atoms. The whole group is selected simultaneously when representing an image patch so that the correlations between the colour channels can be retained. A dictionary training method is also designed in which the two dictionaries are trained jointly to ensure that the corresponding LR and HR patches have the same sparse coefficients. Experimental results demonstrate the effectiveness of the proposed method and its robustness to noise.

[1]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[2]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[3]  Xuelong Li,et al.  Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution , 2011, IEEE Journal of Selected Topics in Signal Processing.

[4]  Zheng Liu,et al.  Learning-based super resolution using kernel partial least squares , 2011, Image Vis. Comput..

[5]  Quan Pan,et al.  Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Yonina C. Eldar,et al.  Robust Recovery of Signals From a Structured Union of Subspaces , 2008, IEEE Transactions on Information Theory.

[7]  Hua Huang,et al.  Neighbor embedding based super-resolution algorithm through edge detection and feature selection , 2009, Pattern Recognit. Lett..

[8]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

[9]  Michael Elad,et al.  On the Role of Sparse and Redundant Representations in Image Processing , 2010, Proceedings of the IEEE.

[10]  ZhangLei,et al.  An edge-guided image interpolation algorithm via directional filtering and data fusion , 2006 .

[11]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[12]  Xuelong Li,et al.  Joint Learning for Single-Image Super-Resolution via a Coupled Constraint , 2012, IEEE Transactions on Image Processing.

[13]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Wan-Chi Siu,et al.  Single image super-resolution using Gaussian process regression , 2011, CVPR 2011.

[15]  D. Yeung,et al.  Super-resolution through neighbor embedding , 2004, CVPR 2004.

[16]  Thomas S. Huang,et al.  Coupled Dictionary Training for Image Super-Resolution , 2012, IEEE Transactions on Image Processing.

[17]  Wen Gao,et al.  Image interpolation via regularized local linear regression , 2011, 28th Picture Coding Symposium.

[18]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  Rabab K. Ward,et al.  Compressed sensing of color images , 2010, Signal Process..

[20]  Lei Zhang,et al.  An edge-guided image interpolation algorithm via directional filtering and data fusion , 2006, IEEE Transactions on Image Processing.

[21]  Pierre Vandergheynst,et al.  Compressed Sensing and Redundant Dictionaries , 2007, IEEE Transactions on Information Theory.

[22]  Shutao Li,et al.  Infrared surveillance image super resolution via group sparse representation , 2013 .

[23]  Babak Hassibi,et al.  On the Reconstruction of Block-Sparse Signals With an Optimal Number of Measurements , 2008, IEEE Transactions on Signal Processing.

[24]  Dit-Yan Yeung,et al.  Image Hallucination Using Neighbor Embedding over Visual Primitive Manifolds , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[26]  William T. Freeman,et al.  Example-Based Super-Resolution , 2002, IEEE Computer Graphics and Applications.

[27]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.