Super-resolution of human face image using canonical correlation analysis

作者:

Highlights:

摘要

Super-resolution reconstruction of face image is the problem of reconstructing a high resolution face image from one or more low resolution face images. Assuming that high and low resolution images share similar intrinsic geometries, various recent super-resolution methods reconstruct high resolution images based on a weights determined from nearest neighbors in the local embedding of low resolution images. These methods suffer disadvantages from the finite number of samples and the nature of manifold learning techniques, and hence yield unrealistic reconstructed images.To address the problem, we apply canonical correlation analysis (CCA), which maximizes the correlation between the local neighbor relationships of high and low resolution images. We use it separately for reconstruction of global face appearance, and facial details. Experiments using a collection of frontal human faces show that the proposed algorithm improves reconstruction quality over existing state-of-the-art super-resolution algorithms, both visually, and using a quantitative peak signal-to-noise ratio assessment.

论文关键词:Human face,Super-resolution,Canonical correlation analysis,Manifold learning,Neighbor reconstruction

论文评审过程:Received 7 May 2009, Revised 15 January 2010, Accepted 11 February 2010, Available online 17 February 2010.

论文官网地址:https://doi.org/10.1016/j.patcog.2010.02.007