Wavelet based illumination invariant preprocessing in face recognition

Y. Z. Goh, Andrew B.J. Teoh, Michael K.O. Goh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Citations (Scopus)

Abstract

Performance of face recognition system has not been satisfied due to the change of illumination on facial image. Thus, there were many proposals that dealing with illumination compensation in face recognition in the past decades. In this paper, we propose a wavelet based illumination invariant algorithm based on the illumination-reflectance model. The proposed method aims to remove illumination component. This can be done by setting the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results.

Original languageEnglish
Title of host publicationProceedings - 1st International Congress on Image and Signal Processing, CISP 2008
Pages421-425
Number of pages5
Volume3
DOIs
Publication statusPublished - 2008 Sep 25
Event1st International Congress on Image and Signal Processing, CISP 2008 - Sanya, Hainan, China
Duration: 2008 May 272008 May 30

Other

Other1st International Congress on Image and Signal Processing, CISP 2008
CountryChina
CitySanya, Hainan
Period08/5/2708/5/30

Fingerprint

Face recognition
Lighting

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Goh, Y. Z., Teoh, A. B. J., & Goh, M. K. O. (2008). Wavelet based illumination invariant preprocessing in face recognition. In Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008 (Vol. 3, pp. 421-425). [4566519] https://doi.org/10.1109/CISP.2008.335
Goh, Y. Z. ; Teoh, Andrew B.J. ; Goh, Michael K.O. / Wavelet based illumination invariant preprocessing in face recognition. Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008. Vol. 3 2008. pp. 421-425
@inproceedings{304f7d53aee1447f989c3c70c9bd5901,
title = "Wavelet based illumination invariant preprocessing in face recognition",
abstract = "Performance of face recognition system has not been satisfied due to the change of illumination on facial image. Thus, there were many proposals that dealing with illumination compensation in face recognition in the past decades. In this paper, we propose a wavelet based illumination invariant algorithm based on the illumination-reflectance model. The proposed method aims to remove illumination component. This can be done by setting the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results.",
author = "Goh, {Y. Z.} and Teoh, {Andrew B.J.} and Goh, {Michael K.O.}",
year = "2008",
month = "9",
day = "25",
doi = "10.1109/CISP.2008.335",
language = "English",
isbn = "9780769531199",
volume = "3",
pages = "421--425",
booktitle = "Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008",

}

Goh, YZ, Teoh, ABJ & Goh, MKO 2008, Wavelet based illumination invariant preprocessing in face recognition. in Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008. vol. 3, 4566519, pp. 421-425, 1st International Congress on Image and Signal Processing, CISP 2008, Sanya, Hainan, China, 08/5/27. https://doi.org/10.1109/CISP.2008.335

Wavelet based illumination invariant preprocessing in face recognition. / Goh, Y. Z.; Teoh, Andrew B.J.; Goh, Michael K.O.

Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008. Vol. 3 2008. p. 421-425 4566519.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Wavelet based illumination invariant preprocessing in face recognition

AU - Goh, Y. Z.

AU - Teoh, Andrew B.J.

AU - Goh, Michael K.O.

PY - 2008/9/25

Y1 - 2008/9/25

N2 - Performance of face recognition system has not been satisfied due to the change of illumination on facial image. Thus, there were many proposals that dealing with illumination compensation in face recognition in the past decades. In this paper, we propose a wavelet based illumination invariant algorithm based on the illumination-reflectance model. The proposed method aims to remove illumination component. This can be done by setting the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results.

AB - Performance of face recognition system has not been satisfied due to the change of illumination on facial image. Thus, there were many proposals that dealing with illumination compensation in face recognition in the past decades. In this paper, we propose a wavelet based illumination invariant algorithm based on the illumination-reflectance model. The proposed method aims to remove illumination component. This can be done by setting the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results.

UR - http://www.scopus.com/inward/record.url?scp=52149099874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52149099874&partnerID=8YFLogxK

U2 - 10.1109/CISP.2008.335

DO - 10.1109/CISP.2008.335

M3 - Conference contribution

SN - 9780769531199

VL - 3

SP - 421

EP - 425

BT - Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008

ER -

Goh YZ, Teoh ABJ, Goh MKO. Wavelet based illumination invariant preprocessing in face recognition. In Proceedings - 1st International Congress on Image and Signal Processing, CISP 2008. Vol. 3. 2008. p. 421-425. 4566519 https://doi.org/10.1109/CISP.2008.335