A neural 3-D object recognition architecture using optimized Gabor filters

Author

Heidemann, Gunther ; Ritter, Helge

Author_Institution

Inst. fur Neuroinf., Bielefeld Univ., Germany

Volume

4

fYear

1996

fDate

25-29 Aug 1996

Firstpage

70

Abstract

We present an object recognition architecture based on feature extraction by Gabor filter kernels and feature classification by an artificial neural network. The parameters of the Gabor filters are optimized to the specific problem by minimizing an energy function. Such Gabor filters extract features that can be more easily classified by the neural network. Moreover, the feature space is low-dimensional so feature extraction does not require much computational effort. The object recognition system is implemented on a Datacube and works in real-time

Keywords

feature extraction; filtering theory; image classification; object recognition; optimisation; self-organising feature maps; stereo image processing; 3D object recognition; Datacube; energy function minimisation; feature classification; feature extraction; feature space; local linear map network; neural networks; optimisation; optimized Gabor filters; real-time systems; Artificial neural networks; Computer vision; Detectors; Feature extraction; Gabor filters; Image segmentation; Lighting; Noise robustness; Object recognition; Real time systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.547236

Filename

547236