A what-and-where neural network for invariant image preprocessing

Author

Carpenter, Gail A. ; Grossberg, Stephen ; Lesher, Gregory W.

Author_Institution

Boston Univ., MA, USA

Volume

3

fYear

1992

fDate

7-11 Jun 1992

Firstpage

303

Abstract

A feedforward neural networks for invariant image preprocessing is proposed that represents the position, orientation, and size of an image figure (where it is) in a multiplexed spatial map. This map is used to generate an invariant representation of the figure that is insensitive to position, orientation, and size for purposes of pattern recognition (what it is). Image recognition is based upon the output from the what channel. A multiscale array of oriented filters, followed by competition between orientations and scales, is used to define the where filter

Keywords

feedforward neural nets; image recognition; feedforward neural networks; image figure; invariant image preprocessing; multiplexed spatial map; multiscale array; orientation; oriented filters; pattern recognition; position; size; what-and-where neural network; Adaptive systems; Biological neural networks; Data preprocessing; Feedforward neural networks; Filters; Fourier transforms; Image recognition; Neural networks; Pattern recognition; Streaming media;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227157

Filename

227157