Learning structurally discriminant features in 3D faces

Author

Sukumar, Sreenivas R. ; Bozdogan, Hamparsum ; Page, David L. ; Koschan, Andreas F. ; Abidi, Mongi A.

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Tennessee, Knoxville, TN, USA

fYear

2008

fDate

12-15 Oct. 2008

Firstpage

1912

Lastpage

1915

Abstract

In this paper, we derive a data mining framework to analyze 3D features on human faces. The framework leverages kernel density estimators, genetic algorithm and an information complexity criterion to identify discriminant feature-clusters of lower dimensionality. We apply this framework on human face anthropometry data of 32 features collected from each of the 300 3D face mesh models. The feature-subsets that we infer as the output establishes domain knowledge for the challenging problem of 3D face recognition with dense 3D gallery models and sparse or low resolution probes.

Keywords

anthropometry; data mining; face recognition; feature extraction; genetic algorithms; learning (artificial intelligence); mesh generation; solid modelling; 3D face mesh model; 3D face recognition; data mining framework; genetic algorithm; geometric feature; human face anthropometry data; information complexity criterion; learning structurally discriminant feature; leverage kernel density estimator; Data mining; Face recognition; Facial features; Feature extraction; Humans; Input variables; Intelligent robots; Linear discriminant analysis; Principal component analysis; Probes; 3D face recognition; dimensionality reduction; feature learning; informative-discrimant face features;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on

Conference_Location

San Diego, CA

ISSN

1522-4880

Print_ISBN

978-1-4244-1765-0

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2008.4712154

Filename

4712154