Neural network architecture for 3D object representation

Author

Cretu, Ana-Maria ; Petriu, Emil M. ; Patry, Gilles G.

Author_Institution

Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont., Canada

fYear

2003

fDate

20-21 Sept. 2003

Firstpage

31

Lastpage

36

Abstract

The paper discusses a neural network architecture for 3D object modeling. A multi-layered feedforward structure having as inputs the 3D-coordinates of the object points is employed to model the object space. Cascaded with a transformation neural network module, the proposed architecture can be used to generate and train 3D objects, perform transformations, set operations and object morphing. A possible application for object recognition is also presented.

Keywords

feedforward neural nets; image morphing; image representation; multilayer perceptrons; neural net architecture; object recognition; 3-dimensional object representation; 3D coordinates; 3D object generation; 3D object training; computer graphics; feedforward structure; neural network architecture; object morphing; object recognition; operation setting; transformation neural network module; Computer architecture; Computer graphics; Equations; Information technology; Neural networks; Neurons; Object recognition; Shape measurement; Solids; Space technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Haptic, Audio and Visual Environments and Their Applications, 2003. HAVE 2003. Proceedings. The 2nd IEEE Internatioal Workshop on

Print_ISBN

0-7803-8108-4

Type

conf

DOI

10.1109/HAVE.2003.1244721

Filename

1244721