Face Image Super-Resolution Using Two-dimensional Locality Preserving Projection
Yuan-Kai Wang, Cai-Ren Huang · 2009
Super-resolution is an important method to reconstruct high-resolution images from low-resolution images. In this paper, a manifold learning algorithm based on two-dimensional locality preserving projection (2D-LPP) is proposed for face image super-resolution. The 2D-LPP detects the intrinsic manifold structure of high space and preserves the structure in low space by projection. The projection approach in the 2D-LPP resolves the out-of-sample problem in embedding-based manifold learning methods, and improves the speed in reducing the dimension of a new sample data. Moreover, the 2D-LPP preserves more accurate manifold structure by directly operating on 2D images rather than flattened 1D vector as PCA and LPP does. Extensive experiments are conducted on the AR and FERET databases. Experimental results show that the proposed method performs better than PCA based super-resolution in both PSNR and time efficiency.