Super-Resolution for Facial Images Based on Local Similarity Preserving

摘要

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.