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

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 b...

Full description

Saved in:
Bibliographic Details
Main Authors: Stormer, A., Rigoll, G.
Format: Conference Proceeding
Language:English
Subjects:
Covariance matrix
Eigenvalues and eigenfunctions
Face detection
Face recognition
Facial features
Hidden Markov models
Image databases
Iterative algorithms
Iterative closest point algorithm
Low pass filters
Statistic modeling
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2008.4712363