A super-resolution algorithm based on adaptive sparse representation

To improve the performance of super-resolution reconstruction of images, a super-resolution algorithm based on adaptive sparse representation is proposed. Our algorithm regards the difference between the high-resolution image and the reconstructed image with Iterative back-projection algorithm as the image's high-frequency characteristic, which is further used for high-resolution dictionary training. And after edge detection, our algorithm adaptively applies sparse representation and Iterative back-projection to edge patches and smooth patches respectively for reconstruction. Experimental results show that, with our algorithm the reconstructed image edges, especially the strong edges, are close to the original high-resolution image, and PSNR could be improved significantly.

[1]  J. D. van Ouwerkerk,et al.  Image super-resolution survey , 2006, Image Vis. Comput..

[2]  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.

[3]  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).

[4]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[5]  Yongyi Yang,et al.  Optical Flow Estimation for a Periodic Image Sequence , 2010, IEEE Transactions on Image Processing.

[6]  Guillermo Sapiro,et al.  Supervised Dictionary Learning , 2008, NIPS.

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

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

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

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

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

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

[13]  Max Mignotte,et al.  A segmentation-based regularization term for image deconvolution , 2006, IEEE Transactions on Image Processing.

[14]  J. Romberg,et al.  Imaging via Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[15]  Yücel Altunbasak,et al.  Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants , 2001, IEEE Trans. Image Process..

[16]  Michael Elad,et al.  Sparse and Redundant Representation Modeling—What Next? , 2012, IEEE Signal Processing Letters.

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

[18]  H Stark,et al.  High-resolution image recovery from image-plane arrays, using convex projections. , 1989, Journal of the Optical Society of America. A, Optics and image science.

[19]  R. Venkatesh Babu,et al.  Super resolution via sparse representation in l1 framework , 2012, ICVGIP '12.

[20]  Michael Elad,et al.  Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation , 2010, IEEE Transactions on Signal Processing.

[21]  Michael Elad,et al.  A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations , 2010, ECCV.

[22]  Michael Elad,et al.  Dictionaries for Sparse Representation Modeling , 2010, Proceedings of the IEEE.

[23]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.