A self-learning visual pattern explorer and recognizer using a higher order neural network

Author

Linhart, Günter ; Dorffner, Georg

Author_Institution

Austrian Res. Inst. for Artificial Intelligence, Vienna, Austria

Volume

3

fYear

1992

fDate

7-11 Jun 1992

Firstpage

705

Abstract

A proposal by M. B. Reid et al. (1989) to improve the efficiency of higher-order neural networks was built into a pattern recognition system that autonomously learns to categorize and recognize patterns independently of their position in an input image. It does this by combining higher-order with first-order networks and the mechanisms known from ART. Its recognition is based on a 16×16 pixel input which contains a section of the image found by a separate centering mechanism. With this system position invariant recognition can be implemented efficiently, while combining all the advantages of the subsystems

Keywords

image recognition; learning (artificial intelligence); neural nets; higher order neural network; input image; pattern recognizer; self-learning; visual pattern explorer; Artificial intelligence; Artificial neural networks; Computational complexity; Computer networks; Image recognition; Neural networks; Pattern recognition; Pixel; Proposals; Subspace constraints;

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.1992.227069

Filename

227069