Face hallucination through KPCA

Yan Liang; Jian Huang Lai; Yao Xian Zou; Wei Shi Zheng; Pong Chi YUEN

doi:10.1109/CISP.2009.5300993

Face hallucination through KPCA

Yan Liang, Jian Huang Lai^*, Yao Xian Zou, Wei Shi Zheng, Pong Chi YUEN

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

4 Citations (Scopus)

Abstract

This paper demonstrates how Kernel Principal Component Analysis (KPCA) can be used for face hallucination. Different with other KPCA-based methods, KPCA in this paper handles samples from two subspaces, namely the high- and low-resolution image spaces. As KPCA learns not only linear features but also non-linear features, it is anticipated that more detailed facial features could be synthesized. We propose a new model and give theoretical analysis on when it is applicable. Algorithm is then developed for implementation. Experiments are conducted to compare the proposed method with the existing well-known face hallucination methods in terms of visual quality and mean square error. Our results are better and encouraging.

Original language	English
Title of host publication	Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09
DOIs	https://doi.org/10.1109/CISP.2009.5300993
Publication status	Published - 2009
Event	2009 2nd International Congress on Image and Signal Processing, CISP'09 - Tianjin, China Duration: 17 Oct 2009 → 19 Oct 2009

Publication series

Name	Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09

Conference

Conference	2009 2nd International Congress on Image and Signal Processing, CISP'09
Country/Territory	China
City	Tianjin
Period	17/10/09 → 19/10/09

Scopus Subject Areas

Computer Vision and Pattern Recognition
Signal Processing
Biomedical Engineering

User-Defined Keywords

Face hallucination
KPCA
Pre-image

Access to Document

10.1109/CISP.2009.5300993

Cite this

@inproceedings{eea842cecf214940b8c664ffeb3ab67a,

title = "Face hallucination through KPCA",

abstract = "This paper demonstrates how Kernel Principal Component Analysis (KPCA) can be used for face hallucination. Different with other KPCA-based methods, KPCA in this paper handles samples from two subspaces, namely the high- and low-resolution image spaces. As KPCA learns not only linear features but also non-linear features, it is anticipated that more detailed facial features could be synthesized. We propose a new model and give theoretical analysis on when it is applicable. Algorithm is then developed for implementation. Experiments are conducted to compare the proposed method with the existing well-known face hallucination methods in terms of visual quality and mean square error. Our results are better and encouraging.",

keywords = "Face hallucination, KPCA, Pre-image",

author = "Yan Liang and Lai, {Jian Huang} and Zou, {Yao Xian} and Zheng, {Wei Shi} and YUEN, {Pong Chi}",

year = "2009",

doi = "10.1109/CISP.2009.5300993",

language = "English",

isbn = "9781424441310",

series = "Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09",

booktitle = "Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09",

}

Liang, Y, Lai, JH, Zou, YX, Zheng, WS & YUEN, PC 2009, Face hallucination through KPCA. in Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09., 5300993, Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09, 2009 2nd International Congress on Image and Signal Processing, CISP'09, Tianjin, China, 17/10/09. https://doi.org/10.1109/CISP.2009.5300993

Face hallucination through KPCA. / Liang, Yan; Lai, Jian Huang; Zou, Yao Xian et al.
Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09. 2009. 5300993 (Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Face hallucination through KPCA

AU - Liang, Yan

AU - Lai, Jian Huang

AU - Zou, Yao Xian

AU - Zheng, Wei Shi

AU - YUEN, Pong Chi

PY - 2009

Y1 - 2009

N2 - This paper demonstrates how Kernel Principal Component Analysis (KPCA) can be used for face hallucination. Different with other KPCA-based methods, KPCA in this paper handles samples from two subspaces, namely the high- and low-resolution image spaces. As KPCA learns not only linear features but also non-linear features, it is anticipated that more detailed facial features could be synthesized. We propose a new model and give theoretical analysis on when it is applicable. Algorithm is then developed for implementation. Experiments are conducted to compare the proposed method with the existing well-known face hallucination methods in terms of visual quality and mean square error. Our results are better and encouraging.

AB - This paper demonstrates how Kernel Principal Component Analysis (KPCA) can be used for face hallucination. Different with other KPCA-based methods, KPCA in this paper handles samples from two subspaces, namely the high- and low-resolution image spaces. As KPCA learns not only linear features but also non-linear features, it is anticipated that more detailed facial features could be synthesized. We propose a new model and give theoretical analysis on when it is applicable. Algorithm is then developed for implementation. Experiments are conducted to compare the proposed method with the existing well-known face hallucination methods in terms of visual quality and mean square error. Our results are better and encouraging.

KW - Face hallucination

KW - KPCA

KW - Pre-image

UR - http://www.scopus.com/inward/record.url?scp=73849133223&partnerID=8YFLogxK

U2 - 10.1109/CISP.2009.5300993

DO - 10.1109/CISP.2009.5300993

M3 - Conference proceeding

AN - SCOPUS:73849133223

SN - 9781424441310

T3 - Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09

BT - Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09

T2 - 2009 2nd International Congress on Image and Signal Processing, CISP'09

Y2 - 17 October 2009 through 19 October 2009

ER -

Face hallucination through KPCA

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this