点击次数：

论文类型：期刊论文

发表时间：2010-07-01

发表刊物：PATTERN RECOGNITION

收录刊物：SCIE、EI

卷号：43

期号：7

页面范围：2532-2543

ISSN号：0031-3203

关键字：Human face; Super-resolution; Canonical correlation analysis; Manifold learning; Neighbor reconstruction

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. (C) 2010 Elsevier Ltd. All rights reserved.