A Local Texture-Constrained Super-Resolution Method

This paper proposes a local texture constrained super-resolution method for the reconstruction of high-resolution image. Through the learned low/high-resolution patches from training images, the intended high resolution patches are reconstructed using neighbor embedding method. The major contributions of this paper are: 1) Local Binary Pattern (LBP) is adopted to classify the patches into different categories, only those patches who have the same pattern with the input patches are used as candidates; 2) Structural SIMilarity (SSIM) metric which can find the patches with texture most similar to the input is used to search the k most suitable patches in the corresponding category. Experiments show that LBP index can provide proper candidate patches and SSIM metric is better than other metric in finding the most texture similarity patches.

[1]  Michal Irani,et al.  Super-resolution from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[3]  Jiejie Zhu,et al.  Context-constrained hallucination for image super-resolution , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[5]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Raanan Fattal,et al.  Image upsampling via texture hallucination , 2010, 2010 IEEE International Conference on Computational Photography (ICCP).

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

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

[9]  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.