Super-Resolution for Facial Images Based on Local Similarity Preserving

To reconstruct low-resolution facial photographs which are in focus and without motion blur, a novel algorithm based on local similarity preserving is proposed. It is based on the theories of local manifold learning. The innovations of the new method include mixing point-based entropy and Euclidian distance to search for the nearest points, adding point-to-patch degradation model to restrict the linear weights and compensating the fusing patch to keep energy coherence. The compensation reduces the algorithm dependence on training sets and keeps the luminance of reconstruction constant. Experiments show that our method can effectively reconstruct 16×12 images with the magnification of 8×8 and the 32×24 facial photographs in focus and without motion blur.

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

[2]  Harry Shum,et al.  Face Hallucination: Theory and Practice , 2007, International Journal of Computer Vision.

[3]  Xiaogang Wang,et al.  Hallucinating face by eigentransformation , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[4]  Huang Hua A survey of super resolution algorithms , 2009 .

[5]  Michael Elad,et al.  Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images , 1997, IEEE Trans. Image Process..

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

[7]  Yu Hu,et al.  From Local Pixel Structure to Global Image Super-Resolution: A New Face Hallucination Framework , 2011, IEEE Transactions on Image Processing.

[8]  Shiguang Shan,et al.  Aligning Coupled Manifolds for Face Hallucination , 2009, IEEE Signal Processing Letters.

[9]  Junping Zhang,et al.  Super-resolution of human face image using canonical correlation analysis , 2010, Pattern Recognit..

[10]  Takeo Kanade,et al.  Hallucinating faces , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[11]  Yueting Zhuang,et al.  Hallucinating faces: LPH super-resolution and neighbor reconstruction for residue compensation , 2007, Pattern Recognit..

[12]  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).