Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/61854| Title: | Face hallucination using orthogonal canonical correlation analysis | Authors: | Zhou, H Lam, KM |
Issue Date: | 2016 | Source: | Journal of electronic imaging, 2016, v. 25, no. 3, 033005 | Abstract: | A two-step face-hallucination framework is proposed to reconstruct a high-resolution (HR) version of a face from an input low-resolution (LR) face, based on learning from LR-HR example face pairs using orthogonal canonical correlation analysis (orthogonal CCA) and linear mapping. In the proposed algorithm, face images are first represented using principal component analysis (PCA). Canonical correlation analysis (CCA) with the orthogonality property is then employed, to maximize the correlation between the PCA coefficients of the LR and the HR face pairs to improve the hallucination performance. The original CCA does not own the orthogonality property, which is crucial for information reconstruction. We propose using orthogonal CCA, which is proven by experiments to achieve a better performance in terms of global face reconstruction. In addition, in the residual-compensation process, a linear-mapping method is proposed to include both the inter-and intrainformation about manifolds of different resolutions. Compared with other state-of-the-art approaches, the proposed framework can achieve a comparable, or even better, performance in terms of global face reconstruction and the visual quality of face hallucination. Experiments on images with various parameter settings and blurring distortions show that the proposed approach is robust and has great potential for real-world applications. | Keywords: | Canonical correlation analysis Face hallucination Linear mapping Orthogonal canonical correlation analysis Super-resolution |
Publisher: | SPIE-International Society for Optical Engineering | Journal: | Journal of electronic imaging | ISSN: | 1017-9909 | EISSN: | 1560-229X | DOI: | 10.1117/1.JEI.25.3.033005 |
| Appears in Collections: | Journal/Magazine Article |
Access
View full-text via PolyU eLinks 
SCOPUSTM
Citations
2
Last Week
0
0
Last month
Citations as of Aug 24, 2020
WEB OF SCIENCETM
Citations
2
Last Week
0
0
Last month
Citations as of Sep 25, 2020
Page view(s)
156
Last Week
6
6
Last month
2
2
Citations as of Sep 21, 2020
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.