Robust face recognition using automatic age normalization

A Lanitis, C J Taylor

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

Abstract

A large number of automatic face recognition systems have been reported in the literature. Many of them are robust to within class appearance variation of subjects such as variation in expression, lighting and pose. However, most of the face identification systems developed, are sensitive to changes in the age of individuals. In this paper we demonstrate that automatic age simulation techniques can be used for designing face recognition systems, robust to ageing variation. In this context, the perceived age of the subjects in the training and test images is modified before the training and classification procedures, so that ageing variation is eliminated. Experimental results demonstrate that the performance of our face recognition system can be improved significantly, when this approach is adopted.
Original languageEnglish
Title of host publication2000 10th Mediterranean Electrotechnical Conference. Information Technology and Electrotechnology for the Mediterranean Countries
Subtitle of host publicationProceedings. MeleCon 2000 (Cat. No.00CH37099)
EditorsCostas Stasopoulos, Andreas Theophanous, Adonis Kellas, Antis M. Constantinou, Kypros Diamantides
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages478-481
Number of pages4
VolumeIII
ISBN (Print)9780780362918, 0780362918
DOIs
Publication statusPublished - May 2000
Event10th Mediterranean Electrotechnical Conference - Lemesos, Cyprus
Duration: 29 May 200031 May 2000

Conference

Conference10th Mediterranean Electrotechnical Conference
Abbreviated titleMeleCon 2000
Country/TerritoryCyprus
CityLemesos
Period29/05/0031/05/00

Keywords

  • Robustness
  • Face recognition
  • Aging
  • System testing
  • Principal component analysis
  • Shape
  • Humans
  • Computer science
  • Educational institutions
  • Biomedical imaging

Fingerprint

Dive into the research topics of 'Robust face recognition using automatic age normalization'. Together they form a unique fingerprint.

Cite this