Feature-based affine-invariant localization of faces

Feature-based affine-invariant localization of faces

We present a novel method for localizing faces in person identification scenarios. Such scenarios involve high resolution images of frontal faces. The proposed algorithm does not require color, copes well in cluttered backgrounds, and accurately localizes faces including eye centers. An extensive an...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence 2005-09, Vol.27 (9), p.1490-1495
Hauptverfasser: Hamouz, M., Kittler, J., Kamarainen, J.K., Paalanen, P., Kalviainen, H., Matas, J.
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Applied sciences
Artificial Intelligence
Authentication
Color
Computer Graphics
Computer science
control theory
systems
Computer Society
Detectors
Exact sciences and technology
Face - anatomy & histology
face authentication
Face detection
Facial features
Humans
Image databases
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image resolution
Index Terms- Face localization
Information Storage and Retrieval - methods
Intelligence
Localization
Numerical Analysis, Computer-Assisted
Pattern analysis
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Performance analysis
Performance evaluation
Shape
Signal Processing, Computer-Assisted
Subtraction Technique
Testing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a novel method for localizing faces in person identification scenarios. Such scenarios involve high resolution images of frontal faces. The proposed algorithm does not require color, copes well in cluttered backgrounds, and accurately localizes faces including eye centers. An extensive analysis and a performance evaluation on the XM2VTS database and on the realistic BioID and BANCA face databases is presented. We show that the algorithm has precision superior to reference methods.
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2005.179