Classifying range images of human faces with Hausdorff distance

Author

Achermann, Bernard ; Bunke, Horst

Author_Institution

Dept. of Comput. Sci., Bern Univ., Switzerland

Volume

2

fYear

2000

fDate

2000

Firstpage

809

Abstract

In this paper, an application of range image analysis in the area of face recognition is described. The process from image acquisition to recognition is presented in detail. Range images are captured with a multisensor system, merged in a fusion step, and preprocessed. Then, a canonical position of the sensed face is determined, and two different representation of the range data, based on point sets and voxel arrays, respectively, are computed. For the recognition step, a 3D version of the partial Hausdorff distance is introduced. Experiments on a database with 240 images of 24 persons yielded nearly perfect results

Keywords

distance measurement; face recognition; image classification; sensor fusion; 3D partial Hausdorff distance; Hausdorff distance; canonical position; face recognition; human face range image classification; image acquisition; image preprocessing; image recognition; multisensor system; point sets; sensor fusion; voxel arrays; Application software; Computer science; Face detection; Face recognition; Humans; Image color analysis; Image recognition; Image sequence analysis; Image storage; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.906199

Filename

906199