Face Identification Algorithm Based on Synthetic Linear Descriptors

Author

Sadykhov, R. Kh ; Samokhval, V.A.

Author_Institution

Comput. Dept., Belarusian State Univ. of Inf. & Radioelectron., Minsk

fYear

2005

fDate

5-7 Sept. 2005

Firstpage

593

Lastpage

595

Abstract

This paper presents appearance-based face identification algorithm by means of synthetic linear filters. The objective of our research is to construct facial descriptor in the form of linear filter, which should produce high and low outputs for intra- and inter-class recognition problem correspondingly. This filter can be synthesized from 2.5 D sparse mesh derived from a given set of images of a person. As ever the filter is created it is then used as facial descriptor, i.e. serves as personal ID for face identification.

Keywords

face recognition; filtering theory; face identification algorithm; facial descriptor; inter-class recognition; intra-class recognition; personal ID; synthetic linear descriptors; synthetic linear filters; Conferences; Face detection; Face recognition; Image storage; Independent component analysis; Informatics; Linear discriminant analysis; Nonlinear filters; Principal component analysis; Training data; appearance-based approach; discriminant function; face recognition; synthetic linear descriptors;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2005. IDAACS 2005. IEEE

Conference_Location

Sofia

Print_ISBN

0-7803-9445-3

Electronic_ISBN

0-7803-9446-1

Type

conf

DOI

10.1109/IDAACS.2005.283053

Filename

4062204