Wavelet based illumination invariant preprocessing in face recognition

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 algor...

Full description

Bibliographic Details
Main Authors: Y. Z., Goh, Andrew B. J., Teoh, Michael K. O., Goh
Format: Conference or Workshop Item
Published: 2008
Subjects:
Online Access:http://shdl.mmu.edu.my/2883/
_version_ 1848790175664046080
author Y. Z., Goh
Andrew B. J., Teoh
Michael K. O., Goh
author_facet Y. Z., Goh
Andrew B. J., Teoh
Michael K. O., Goh
author_sort Y. Z., Goh
building MMU Institutional Repository
collection Online Access
description 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 selling the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results.
first_indexed 2025-11-14T18:08:26Z
format Conference or Workshop Item
id mmu-2883
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:08:26Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling mmu-28832011-09-21T07:26:05Z http://shdl.mmu.edu.my/2883/ Wavelet based illumination invariant preprocessing in face recognition Y. Z., Goh Andrew B. J., Teoh Michael K. O., Goh T Technology (General) QA75.5-76.95 Electronic computers. Computer science 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 selling the coefficients in wavelet approximation subband to zero values. The algorithms are tested on YaleB database and CMU PIE database, with encouraging results. 2008-05 Conference or Workshop Item NonPeerReviewed Y. Z., Goh and Andrew B. J., Teoh and Michael K. O., Goh (2008) Wavelet based illumination invariant preprocessing in face recognition. In: 1st International Congress on Image and Signal Processing , 27-30 MAY 2008 , Sanya, PEOPLES R CHINA. http://apps.webofknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=1&SID=W2mchH3@hBF6CHEhMcN&page=92&doc=917
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
Y. Z., Goh
Andrew B. J., Teoh
Michael K. O., Goh
Wavelet based illumination invariant preprocessing in face recognition
title Wavelet based illumination invariant preprocessing in face recognition
title_full Wavelet based illumination invariant preprocessing in face recognition
title_fullStr Wavelet based illumination invariant preprocessing in face recognition
title_full_unstemmed Wavelet based illumination invariant preprocessing in face recognition
title_short Wavelet based illumination invariant preprocessing in face recognition
title_sort wavelet based illumination invariant preprocessing in face recognition
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2883/
http://shdl.mmu.edu.my/2883/