Illuminated facial preprocessing with wavelet local binary patterns histogram specification

Yi Zheng Goh, Michael Kah Ong Goh, Beng Jin Teoh

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

Abstract

Contemporary 2D face recognition is still a challenging work, especially when lighting varies. Thus, many works of resolving illumination variation in face recognition have been proposed, in the past decades. In this paper, we proposed Wavelet Local Binary Patterns Histogram Specification as a preprocessing technique for illuminated face recognition. Based on wavelet analysis, an illuminated facial image is decomposed into illumination and reflectance components. The illumination component that resides in the low spatial-frequency subband is first removed. Next, the reflectance component that resides in the high and middle spatial-frequency subband is then enhanced with local binary pattern histogram. This technique is promising in achieving better recognition performance on YaleB and CMU PIE face databases in comparison to the results that achieved by existing illumination invariant techniques.

Original languageEnglish
Title of host publicationICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing
DOIs
Publication statusPublished - 2009 Dec 1
Event7th International Conference on Information, Communications and Signal Processing, ICICS 2009 - Macau Fisherman's Wharf, Macao
Duration: 2009 Dec 82009 Dec 10

Other

Other7th International Conference on Information, Communications and Signal Processing, ICICS 2009
CountryMacao
CityMacau Fisherman's Wharf
Period09/12/809/12/10

Fingerprint

Lighting
Specifications
Face recognition
Wavelet analysis

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Goh, Y. Z., Goh, M. K. O., & Teoh, B. J. (2009). Illuminated facial preprocessing with wavelet local binary patterns histogram specification. In ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing [5397475] https://doi.org/10.1109/ICICS.2009.5397475
Goh, Yi Zheng ; Goh, Michael Kah Ong ; Teoh, Beng Jin. / Illuminated facial preprocessing with wavelet local binary patterns histogram specification. ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing. 2009.
@inproceedings{a31d9128a6c845e9a72e1fc5c0dfb088,
title = "Illuminated facial preprocessing with wavelet local binary patterns histogram specification",
abstract = "Contemporary 2D face recognition is still a challenging work, especially when lighting varies. Thus, many works of resolving illumination variation in face recognition have been proposed, in the past decades. In this paper, we proposed Wavelet Local Binary Patterns Histogram Specification as a preprocessing technique for illuminated face recognition. Based on wavelet analysis, an illuminated facial image is decomposed into illumination and reflectance components. The illumination component that resides in the low spatial-frequency subband is first removed. Next, the reflectance component that resides in the high and middle spatial-frequency subband is then enhanced with local binary pattern histogram. This technique is promising in achieving better recognition performance on YaleB and CMU PIE face databases in comparison to the results that achieved by existing illumination invariant techniques.",
author = "Goh, {Yi Zheng} and Goh, {Michael Kah Ong} and Teoh, {Beng Jin}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ICICS.2009.5397475",
language = "English",
isbn = "9781424446575",
booktitle = "ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing",

}

Goh, YZ, Goh, MKO & Teoh, BJ 2009, Illuminated facial preprocessing with wavelet local binary patterns histogram specification. in ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing., 5397475, 7th International Conference on Information, Communications and Signal Processing, ICICS 2009, Macau Fisherman's Wharf, Macao, 09/12/8. https://doi.org/10.1109/ICICS.2009.5397475

Illuminated facial preprocessing with wavelet local binary patterns histogram specification. / Goh, Yi Zheng; Goh, Michael Kah Ong; Teoh, Beng Jin.

ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing. 2009. 5397475.

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

TY - GEN

T1 - Illuminated facial preprocessing with wavelet local binary patterns histogram specification

AU - Goh, Yi Zheng

AU - Goh, Michael Kah Ong

AU - Teoh, Beng Jin

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Contemporary 2D face recognition is still a challenging work, especially when lighting varies. Thus, many works of resolving illumination variation in face recognition have been proposed, in the past decades. In this paper, we proposed Wavelet Local Binary Patterns Histogram Specification as a preprocessing technique for illuminated face recognition. Based on wavelet analysis, an illuminated facial image is decomposed into illumination and reflectance components. The illumination component that resides in the low spatial-frequency subband is first removed. Next, the reflectance component that resides in the high and middle spatial-frequency subband is then enhanced with local binary pattern histogram. This technique is promising in achieving better recognition performance on YaleB and CMU PIE face databases in comparison to the results that achieved by existing illumination invariant techniques.

AB - Contemporary 2D face recognition is still a challenging work, especially when lighting varies. Thus, many works of resolving illumination variation in face recognition have been proposed, in the past decades. In this paper, we proposed Wavelet Local Binary Patterns Histogram Specification as a preprocessing technique for illuminated face recognition. Based on wavelet analysis, an illuminated facial image is decomposed into illumination and reflectance components. The illumination component that resides in the low spatial-frequency subband is first removed. Next, the reflectance component that resides in the high and middle spatial-frequency subband is then enhanced with local binary pattern histogram. This technique is promising in achieving better recognition performance on YaleB and CMU PIE face databases in comparison to the results that achieved by existing illumination invariant techniques.

UR - http://www.scopus.com/inward/record.url?scp=77949642462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949642462&partnerID=8YFLogxK

U2 - 10.1109/ICICS.2009.5397475

DO - 10.1109/ICICS.2009.5397475

M3 - Conference contribution

SN - 9781424446575

BT - ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing

ER -

Goh YZ, Goh MKO, Teoh BJ. Illuminated facial preprocessing with wavelet local binary patterns histogram specification. In ICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing. 2009. 5397475 https://doi.org/10.1109/ICICS.2009.5397475