DocumentCode :
2536816
Title :
Representation of objects in a volumetric frequency domain with application to face recognition
Author :
Ben-Arie, Jezekiel ; Nandy, Dibyendu
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Illinois Univ., Chicago, IL, USA
fYear :
1997
fDate :
17-19 Jun 1997
Firstpage :
615
Lastpage :
620
Abstract :
A novel method for representing 3-D objects that unifies viewer and model centered object representations is presented. A unified 3-D frequency-domain representation (called volumetric/iconic spectral signatures-V/ISS) encapsulates both the spatial structure of the object and a continuum of its views in the same data structure. The frequency-domain image of an object viewed from any direction can be directly extracted employing an extension of the projection slice theorem, where each Fourier-transformed view is a planar slice of the volumetric frequency representation. The V/ISS representation call be employed for pose-invariant recognition of complex objects such as faces. The recognition and pose estimation is based on an efficient matching algorithm in a four dimensional Fourier space. Experimental examples of pose estimation and recognition of faces are also presented
Keywords :
Fourier transforms; data structures; face recognition; frequency-domain analysis; image matching; image representation; object recognition; stereo image processing; 3D object representation; 4D Fourier space; Fourier-transformed view; complex objects; data structure; efficient matching algorithm; face recognition; frequency-domain image extraction; model centered object representations; object spatial structure; object view continuum; pose estimation; pose-invariant recognition; projection slice theorem; unified 3D frequency-domain representation; viewer centered object representations; volumetric frequency domain; volumetric/iconic spectral signatures; Data mining; Data structures; Face recognition; Frequency domain analysis; Image coding; Image recognition; Merging; Object recognition; Shape; Solids;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location :
San Juan
ISSN :
1063-6919
Print_ISBN :
0-8186-7822-4
Type :
conf
DOI :
10.1109/CVPR.1997.609389
Filename :
609389
Link To Document :
بازگشت