Facial fiducial points detection using discriminative filtering on principal components

Author

Waldir, S.S. ; Araujo, G.M. ; da Silva, E.A.B. ; Goldenstein, Siome K.

Author_Institution

PEE, Univ. Fed. do Rio de Janeiro, Rio de Janeiro, Brazil

fYear

2010

fDate

26-29 Sept. 2010

Firstpage

2681

Lastpage

2684

Abstract

The Discriminative Filtering technique performs pattern recognition using a two-dimensional filter. It has a closed-form design, based on the pattern and the statistics of the image set. Here, we investigate the use of Discriminative Filtering for detecting fiducial points in human faces. We show that designing discriminative filters for the principal components increases robustness. The method is assessed in a fiducial points detection framework using a Gentle AdaBoost classifier.

Keywords

face recognition; image classification; principal component analysis; statistical analysis; AdaBoost classifier; discriminative filtering; facial fiducial points detection; pattern recognition; principal component analysis; statistics; Covariance matrix; Filtering; Humans; Image restoration; Principal component analysis; Support vector machines; Training; AdaBoost; Discriminative Filtering; Fiducial Points; Pattern Recognition; Principal Component Analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2010 17th IEEE International Conference on

Conference_Location

Hong Kong

ISSN

1522-4880

Print_ISBN

978-1-4244-7992-4

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2010.5651849

Filename

5651849