A multi-step alignment scheme for face recognition in range images

Andre Störmer, Gerhard Rigoll

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

5 Zitate (Scopus)

Abstract

Face Recognition in range images is a challenging task, especially if the pose of the shown face is unknown. To solve this, an alignment procedure consisting of facial feature hypotheses extraction by invariant curvature features, PCA-based classification and Iterative Closest Point alignment will be introduced to create aligned and normalized patches. These patches will then be used in a recognition algorithm, a discrete Pseudo 2-Dimensional Hidden Markov Model approach based on vector quantized DCTmod2 features. The results of this processing chain are discussed and compared to previous works.

OriginalspracheEnglisch
Titel2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
Seiten2748-2751
Seitenumfang4
DOIs
PublikationsstatusVeröffentlicht - 2008
Veranstaltung2008 IEEE International Conference on Image Processing, ICIP 2008 - San Diego, CA, USA/Vereinigte Staaten
Dauer: 12 Okt. 200815 Okt. 2008

Publikationsreihe

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Konferenz

Konferenz2008 IEEE International Conference on Image Processing, ICIP 2008
Land/GebietUSA/Vereinigte Staaten
OrtSan Diego, CA
Zeitraum12/10/0815/10/08

Fingerprint

Untersuchen Sie die Forschungsthemen von „A multi-step alignment scheme for face recognition in range images“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren