A face hallucination algorithm via KPLS-eigentransformation model

Xiaoguang Li; Qing Xia; Li Zhuo; Kin Man Lam

doi:10.1109/ICSPCC.2012.6335599

A face hallucination algorithm via KPLS-eigentransformation model

Xiaoguang Li, Qing Xia, Li Zhuo, 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

5 Citations (Scopus)

Abstract

In this paper, we present a novel eigentransformation based algorithm for face hallucination. The traditional eigentransformation method is a linear subspace approach, which represents an image as a linear combination of training samples. Consequently, it cannot effectively represent the relationship between the low resolution facial images and the corresponding high-resolution version. In our algorithm, a Kernel Partial Least Squares (KPLS) predictor is introduced into the eigentransformation model for solving the High Resolution (HR) image form a Low Resolution (LR) facial image. We have compared our proposed method with some current Super Resolution (SR) algorithms using different zooming factors. Experimental results show that our algorithm provides improved performances over the compared methods in terms of both visual quality and numerical errors.

Original language	English
Title of host publication	2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
Pages	462-467
Number of pages	6
DOIs	https://doi.org/10.1109/ICSPCC.2012.6335599
Publication status	Published - 26 Nov 2012
Event	2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012 - Hong Kong, Hong Kong Duration: 12 Aug 2012 → 15 Aug 2012

Conference

Conference	2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012
Country/Territory	Hong Kong
City	Hong Kong
Period	12/08/12 → 15/08/12

Keywords

Eigentransformation
face halluciantion
Image super resolution
Kernel partial least squares

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

More information

10.1109/ICSPCC.2012.6335599

Cite this

@inproceedings{205dfc745b3b479ab706ab39f907ecd5,

title = "A face hallucination algorithm via KPLS-eigentransformation model",

abstract = "In this paper, we present a novel eigentransformation based algorithm for face hallucination. The traditional eigentransformation method is a linear subspace approach, which represents an image as a linear combination of training samples. Consequently, it cannot effectively represent the relationship between the low resolution facial images and the corresponding high-resolution version. In our algorithm, a Kernel Partial Least Squares (KPLS) predictor is introduced into the eigentransformation model for solving the High Resolution (HR) image form a Low Resolution (LR) facial image. We have compared our proposed method with some current Super Resolution (SR) algorithms using different zooming factors. Experimental results show that our algorithm provides improved performances over the compared methods in terms of both visual quality and numerical errors.",

keywords = "Eigentransformation, face halluciantion, Image super resolution, Kernel partial least squares",

author = "Xiaoguang Li and Qing Xia and Li Zhuo and Lam, {Kin Man}",

year = "2012",

month = nov,

day = "26",

doi = "10.1109/ICSPCC.2012.6335599",

language = "English",

isbn = "9781467321938",

pages = "462--467",

booktitle = "2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012",

note = "2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012 ; Conference date: 12-08-2012 Through 15-08-2012",

}

Li, X, Xia, Q, Zhuo, L & Lam, KM 2012, A face hallucination algorithm via KPLS-eigentransformation model. in 2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012., 6335599, pp. 462-467, 2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012, Hong Kong, Hong Kong, 12/08/12. https://doi.org/10.1109/ICSPCC.2012.6335599

A face hallucination algorithm via KPLS-eigentransformation model. / Li, Xiaoguang; Xia, Qing; Zhuo, Li et al.
2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012. 2012. p. 462-467 6335599.

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

TY - GEN

T1 - A face hallucination algorithm via KPLS-eigentransformation model

AU - Li, Xiaoguang

AU - Xia, Qing

AU - Zhuo, Li

AU - Lam, Kin Man

PY - 2012/11/26

Y1 - 2012/11/26

N2 - In this paper, we present a novel eigentransformation based algorithm for face hallucination. The traditional eigentransformation method is a linear subspace approach, which represents an image as a linear combination of training samples. Consequently, it cannot effectively represent the relationship between the low resolution facial images and the corresponding high-resolution version. In our algorithm, a Kernel Partial Least Squares (KPLS) predictor is introduced into the eigentransformation model for solving the High Resolution (HR) image form a Low Resolution (LR) facial image. We have compared our proposed method with some current Super Resolution (SR) algorithms using different zooming factors. Experimental results show that our algorithm provides improved performances over the compared methods in terms of both visual quality and numerical errors.

AB - In this paper, we present a novel eigentransformation based algorithm for face hallucination. The traditional eigentransformation method is a linear subspace approach, which represents an image as a linear combination of training samples. Consequently, it cannot effectively represent the relationship between the low resolution facial images and the corresponding high-resolution version. In our algorithm, a Kernel Partial Least Squares (KPLS) predictor is introduced into the eigentransformation model for solving the High Resolution (HR) image form a Low Resolution (LR) facial image. We have compared our proposed method with some current Super Resolution (SR) algorithms using different zooming factors. Experimental results show that our algorithm provides improved performances over the compared methods in terms of both visual quality and numerical errors.

KW - Eigentransformation

KW - face halluciantion

KW - Image super resolution

KW - Kernel partial least squares

UR - http://www.scopus.com/inward/record.url?scp=84869379887&partnerID=8YFLogxK

U2 - 10.1109/ICSPCC.2012.6335599

DO - 10.1109/ICSPCC.2012.6335599

M3 - Conference article published in proceeding or book

SN - 9781467321938

SP - 462

EP - 467

BT - 2012 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012

T2 - 2012 2nd IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2012

Y2 - 12 August 2012 through 15 August 2012

ER -

A face hallucination algorithm via KPLS-eigentransformation model

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this