Image super-resolution enhancement based on online learning and blind sparse decomposition

This paper presents a different learning-based image super-resolution enhancement method based on blind sparse decomposition, in order to improve its resolution of a degraded one. Firstly, sparse decomposition based image super-resolution enhancement model is put forward according to the geometrical invariability of local image structures under different conditions of resolution. Secondly, for reducing the complexity of dictionary learning and enhancing adaptive representation ability of dictionary atoms, the over-complete dictionary is constructed using online learning fashion of the given low resolution image. Thirdly, since the fixed sparsity of the conventional matching pursuit algorithms for sparse decomposition can not fit all types of patches, the approach to sparse decomposition with blind sparsity can achieve relatively higher accurate sparse representation of an image patch. Lastly, atoms of high resolution dictionary and coefficients of representation of the given low-resolution image are synthesized to the desired SR image. Experimental results of the synthetic and real data demonstrate that the suggested framework can eliminate blurring degradation and annoying edge artifacts in the resulting images. The proposed method can be effectively applied to resolution enhancement of the single-frame low-resolution image.

[1]  Michael Elad,et al.  From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images , 2009, SIAM Rev..

[2]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[3]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[4]  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.

[5]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[6]  Michael Elad,et al.  Generalizing the Nonlocal-Means to Super-Resolution Reconstruction , 2009, IEEE Transactions on Image Processing.

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

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

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

[10]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Thong T. Do,et al.  Sparsity adaptive matching pursuit algorithm for practical compressed sensing , 2008, 2008 42nd Asilomar Conference on Signals, Systems and Computers.

[12]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[13]  T. Blumensath,et al.  On the Difference Between Orthogonal Matching Pursuit and Orthogonal Least Squares , 2007 .

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[16]  S. Mallat,et al.  Adaptive greedy approximations , 1997 .

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

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

[19]  Chi-Keung Tang,et al.  Limits of Learning-Based Superresolution Algorithms , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[20]  Deanna Needell,et al.  Topics in Compressed Sensing , 2009, ArXiv.