Global face reconstruction for face hallucination using orthogonal canonical correlation analysis

Huiling Zhou; Jiwei Hu; Kin Man Lam

doi:10.1109/APSIPA.2015.7415328

Global face reconstruction for face hallucination using orthogonal canonical correlation analysis

Huiling Zhou, Jiwei Hu, Kin Man Lam

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

8 Citations (Scopus)

Abstract

In this paper, a global face reconstruction framework for face hallucination is proposed to globally reconstruct a high-resolution (HR) version of a face from an input low-resolution (LR) face, based on learning from LR-HR face pairs using orthogonal canonical correlation analysis (orthogonal CCA). In our proposed algorithm, face images are first represented using principal component analysis (PCA). CCA with the orthogonality property is then employed to maximize the correlation between the PCA coefficients of the LR and the HR face pairs so as to improve the hallucination performance. The original CCA does not own the orthogonality property, which is crucial for information reconstruction. In this paper, we utilize an orthogonal variant of CCA, which has been proven by experiments to achieve a better performance than the original CCA in terms of global face reconstruction.

Original language	English
Title of host publication	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
Publisher	IEEE
Pages	537-542
Number of pages	6
ISBN (Electronic)	9789881476807
DOIs	https://doi.org/10.1109/APSIPA.2015.7415328
Publication status	Published - 19 Feb 2016
Event	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong Duration: 16 Dec 2015 → 19 Dec 2015

Conference

Conference	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
Country/Territory	Hong Kong
City	Hong Kong
Period	16/12/15 → 19/12/15

ASJC Scopus subject areas

Artificial Intelligence
Modelling and Simulation
Signal Processing

More information

10.1109/APSIPA.2015.7415328

Cite this

@inproceedings{6c9fbf29c7374e30b71e16562af1affb,

title = "Global face reconstruction for face hallucination using orthogonal canonical correlation analysis",

abstract = "In this paper, a global face reconstruction framework for face hallucination is proposed to globally reconstruct a high-resolution (HR) version of a face from an input low-resolution (LR) face, based on learning from LR-HR face pairs using orthogonal canonical correlation analysis (orthogonal CCA). In our proposed algorithm, face images are first represented using principal component analysis (PCA). CCA with the orthogonality property is then employed to maximize the correlation between the PCA coefficients of the LR and the HR face pairs so as to improve the hallucination performance. The original CCA does not own the orthogonality property, which is crucial for information reconstruction. In this paper, we utilize an orthogonal variant of CCA, which has been proven by experiments to achieve a better performance than the original CCA in terms of global face reconstruction.",

author = "Huiling Zhou and Jiwei Hu and Lam, {Kin Man}",

year = "2016",

month = feb,

day = "19",

doi = "10.1109/APSIPA.2015.7415328",

language = "English",

pages = "537--542",

booktitle = "2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015",

publisher = "IEEE",

address = "United States",

note = "2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 ; Conference date: 16-12-2015 Through 19-12-2015",

}

Zhou, H, Hu, J & Lam, KM 2016, Global face reconstruction for face hallucination using orthogonal canonical correlation analysis. in 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015., 7415328, IEEE, pp. 537-542, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015, Hong Kong, Hong Kong, 16/12/15. https://doi.org/10.1109/APSIPA.2015.7415328

Global face reconstruction for face hallucination using orthogonal canonical correlation analysis. / Zhou, Huiling; Hu, Jiwei; Lam, Kin Man.
2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. IEEE, 2016. p. 537-542 7415328.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Global face reconstruction for face hallucination using orthogonal canonical correlation analysis

AU - Zhou, Huiling

AU - Hu, Jiwei

AU - Lam, Kin Man

PY - 2016/2/19

Y1 - 2016/2/19

N2 - In this paper, a global face reconstruction framework for face hallucination is proposed to globally reconstruct a high-resolution (HR) version of a face from an input low-resolution (LR) face, based on learning from LR-HR face pairs using orthogonal canonical correlation analysis (orthogonal CCA). In our proposed algorithm, face images are first represented using principal component analysis (PCA). CCA with the orthogonality property is then employed to maximize the correlation between the PCA coefficients of the LR and the HR face pairs so as to improve the hallucination performance. The original CCA does not own the orthogonality property, which is crucial for information reconstruction. In this paper, we utilize an orthogonal variant of CCA, which has been proven by experiments to achieve a better performance than the original CCA in terms of global face reconstruction.

AB - In this paper, a global face reconstruction framework for face hallucination is proposed to globally reconstruct a high-resolution (HR) version of a face from an input low-resolution (LR) face, based on learning from LR-HR face pairs using orthogonal canonical correlation analysis (orthogonal CCA). In our proposed algorithm, face images are first represented using principal component analysis (PCA). CCA with the orthogonality property is then employed to maximize the correlation between the PCA coefficients of the LR and the HR face pairs so as to improve the hallucination performance. The original CCA does not own the orthogonality property, which is crucial for information reconstruction. In this paper, we utilize an orthogonal variant of CCA, which has been proven by experiments to achieve a better performance than the original CCA in terms of global face reconstruction.

UR - http://www.scopus.com/inward/record.url?scp=84986208861&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2015.7415328

DO - 10.1109/APSIPA.2015.7415328

M3 - Conference article published in proceeding or book

SP - 537

EP - 542

BT - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015

PB - IEEE

T2 - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015

Y2 - 16 December 2015 through 19 December 2015

ER -

Global face reconstruction for face hallucination using orthogonal canonical correlation analysis

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this