umu.sePublications
Change search
ReferencesLink to record
Permanent link

Direct link
Face identification from one single sample face image
Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics.
2004 (English)In: ICIP: 2004 international conference on image processing, vols 1-5, New York: IEEE conference proceedings, 2004, Vol. 2, 1401-1404 p.Conference paper (Refereed)Text
Abstract [en]

This paper is addressing a challenging face recognition problem: Face Identification From One Single Face Image. We present a novel approach to face identification, which is capable to identify a person from face images that are significantly different from the sample image in terms of illumination, camera view angles and expressions, The approach is based on a new measurement of dissimilarily between the two face images. A person is identified based on the smallest dissimilarity, which is the Summation of the dissimilarilies of all pairs of observations extracted from the face image on both vertical and horizontal directions. Our experiment results tested on both the AR face database and the CMU PIE face database show that the proposed method outperforms the PCA, LDA, LFA based approaches.

Place, publisher, year, edition, pages
New York: IEEE conference proceedings, 2004. Vol. 2, 1401-1404 p.
Series
, IEEE International Conference on Image Processing (ICIP), ISSN 1522-4880
National Category
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-122189DOI: 10.1109/ICIP.2004.1419764ISI: 000228043501173ISBN: 0-7803-8554-3OAI: oai:DiVA.org:umu-122189DiVA: diva2:938177
Conference
International Conference on Image Processing (ICIP 2004), OCT 24-27, 2004, Singapore, SINGAPORE
Available from: 2016-06-16 Created: 2016-06-15 Last updated: 2016-06-16Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Le, Hung-Son
By organisation
Department of Applied Physics and Electronics
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 2 hits
ReferencesLink to record
Permanent link

Direct link