Enhanced multiband feature technique for face recognition under varying illumination

Sue Inn Ch'ng, Kah Phooi Seng, Li Minn Ang

Research output: Book chapter/Published conference paperConference paper

2 Citations (Scopus)

Abstract

This paper presents an enhanced multiband feature technique to improve the performance of face recognition under varying illumination. First, the illumination invariant subbands are extracted using wavelet packet transform and multiband feature selector. Then, histogram equalization is applied to the selected subbands to enhance the contrast of the subband (global). To reduce the noise and enhance the fine details of the facial features (local), an unsharp filter is subsequently applied to the histogram equalized subband. The unsharp filter is created by combining a Gaussian low pass filter and a negative Laplacian operator. The recognition performance of the proposed enhancement scheme is validated against the Yale B database. An improvement in recognition rate has been observed when the enhancement scheme is compared to the original unenhanced subband.

Original languageEnglish
Title of host publicationIEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet
Pages61-64
Number of pages4
DOIs
Publication statusPublished - 01 Dec 2010
EventIEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Kuala Lumpur, Malaysia
Duration: 20 Nov 201021 Nov 2010

Conference

ConferenceIEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010
CountryMalaysia
CityKuala Lumpur
Period20/11/1021/11/10

Fingerprint

Face recognition
Lighting
Low pass filters

Cite this

Ch'ng, S. I., Seng, K. P., & Ang, L. M. (2010). Enhanced multiband feature technique for face recognition under varying illumination. In IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet (pp. 61-64). [5687006] https://doi.org/10.1109/STUDENT.2010.5687006
Ch'ng, Sue Inn ; Seng, Kah Phooi ; Ang, Li Minn. / Enhanced multiband feature technique for face recognition under varying illumination. IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet. 2010. pp. 61-64
@inproceedings{8e280ee9136e430f9fb3a9bd36c3b631,
title = "Enhanced multiband feature technique for face recognition under varying illumination",
abstract = "This paper presents an enhanced multiband feature technique to improve the performance of face recognition under varying illumination. First, the illumination invariant subbands are extracted using wavelet packet transform and multiband feature selector. Then, histogram equalization is applied to the selected subbands to enhance the contrast of the subband (global). To reduce the noise and enhance the fine details of the facial features (local), an unsharp filter is subsequently applied to the histogram equalized subband. The unsharp filter is created by combining a Gaussian low pass filter and a negative Laplacian operator. The recognition performance of the proposed enhancement scheme is validated against the Yale B database. An improvement in recognition rate has been observed when the enhancement scheme is compared to the original unenhanced subband.",
keywords = "Gaussian low pass filter, Laplacian operator, Multi band feature technique, Wavelet packet transform",
author = "Ch'ng, {Sue Inn} and Seng, {Kah Phooi} and Ang, {Li Minn}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/STUDENT.2010.5687006",
language = "English",
isbn = "9781424475032",
pages = "61--64",
booktitle = "IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet",

}

Ch'ng, SI, Seng, KP & Ang, LM 2010, Enhanced multiband feature technique for face recognition under varying illumination. in IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet., 5687006, pp. 61-64, IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010, Kuala Lumpur, Malaysia, 20/11/10. https://doi.org/10.1109/STUDENT.2010.5687006

Enhanced multiband feature technique for face recognition under varying illumination. / Ch'ng, Sue Inn; Seng, Kah Phooi; Ang, Li Minn.

IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet. 2010. p. 61-64 5687006.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Enhanced multiband feature technique for face recognition under varying illumination

AU - Ch'ng, Sue Inn

AU - Seng, Kah Phooi

AU - Ang, Li Minn

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents an enhanced multiband feature technique to improve the performance of face recognition under varying illumination. First, the illumination invariant subbands are extracted using wavelet packet transform and multiband feature selector. Then, histogram equalization is applied to the selected subbands to enhance the contrast of the subband (global). To reduce the noise and enhance the fine details of the facial features (local), an unsharp filter is subsequently applied to the histogram equalized subband. The unsharp filter is created by combining a Gaussian low pass filter and a negative Laplacian operator. The recognition performance of the proposed enhancement scheme is validated against the Yale B database. An improvement in recognition rate has been observed when the enhancement scheme is compared to the original unenhanced subband.

AB - This paper presents an enhanced multiband feature technique to improve the performance of face recognition under varying illumination. First, the illumination invariant subbands are extracted using wavelet packet transform and multiband feature selector. Then, histogram equalization is applied to the selected subbands to enhance the contrast of the subband (global). To reduce the noise and enhance the fine details of the facial features (local), an unsharp filter is subsequently applied to the histogram equalized subband. The unsharp filter is created by combining a Gaussian low pass filter and a negative Laplacian operator. The recognition performance of the proposed enhancement scheme is validated against the Yale B database. An improvement in recognition rate has been observed when the enhancement scheme is compared to the original unenhanced subband.

KW - Gaussian low pass filter

KW - Laplacian operator

KW - Multi band feature technique

KW - Wavelet packet transform

UR - http://www.scopus.com/inward/record.url?scp=79851469431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851469431&partnerID=8YFLogxK

U2 - 10.1109/STUDENT.2010.5687006

DO - 10.1109/STUDENT.2010.5687006

M3 - Conference paper

AN - SCOPUS:79851469431

SN - 9781424475032

SP - 61

EP - 64

BT - IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet

ER -

Ch'ng SI, Seng KP, Ang LM. Enhanced multiband feature technique for face recognition under varying illumination. In IEEE Conference on Sustainable Utilization and Development in Engineering and Technology 2010, STUDENT 2010 - Conference Booklet. 2010. p. 61-64. 5687006 https://doi.org/10.1109/STUDENT.2010.5687006