Aydinlanma alt-uzaylarma dayali gürbüz yüz tanima

Translated title of the contribution: Illumination subspaces based robust face recognition

D. Kern*, H. K. Ekenel, R. Stiefelhagen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper a face recognition system that is based on illumination subspaces is presented. In this system, first, the dominant illumination directions are learned using a clustering algorithm. Three main illumination directions are observed: Ones that have frontal illumination, illumination from left and right sides. After determining the dominant illumination direction classes, the face space is divided into these classes to separate the variations caused by illumination from the variations caused by different identities. Then illumination subspaces based face recognition approach is used to benefit from the additional knowledge of the illumination direction. The proposed approach is tested on the images from the illumination and lighting subsets of the CMU PIE database. The experimental results show that by utilizing knowledge of illumination direction and using illumination subspaces based face recognition, the performance is significantly improved.

Translated title of the contributionIllumination subspaces based robust face recognition
Original languageTurkish
Title of host publication2006 IEEE 14th Signal Processing and Communications Applications Conference
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 IEEE 14th Signal Processing and Communications Applications - Antalya, Turkey
Duration: 17 Apr 200619 Apr 2006

Publication series

Name2006 IEEE 14th Signal Processing and Communications Applications Conference
Volume2006

Conference

Conference2006 IEEE 14th Signal Processing and Communications Applications
Country/TerritoryTurkey
CityAntalya
Period17/04/0619/04/06

Fingerprint

Dive into the research topics of 'Illumination subspaces based robust face recognition'. Together they form a unique fingerprint.

Cite this