Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers

The classification and recognition of two-dimensional patterns independently of their position, orientation, and size by using high-order networks are discussed. A method is introduced for reducing and controlling the number of weights of a third-order network used for invariant pattern recognition....

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks 1992-03, Vol.3 (2), p.241-251
Main Authors: Perantonis, S.J., Lisboa, P.J.G.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Feature extraction
Handwriting recognition
Image recognition
Image resolution
Message-oriented middleware
Moment methods
Neural networks
Pattern recognition
Pixel
Size control
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The classification and recognition of two-dimensional patterns independently of their position, orientation, and size by using high-order networks are discussed. A method is introduced for reducing and controlling the number of weights of a third-order network used for invariant pattern recognition. The method leads to economical networks that exhibit high recognition rates for translated, rotated, and scaled, as well as locally distorted, patterns. The performance of these networks at recognizing types and handwritten numerals independently of their position, size, and orientation is compared with and found superior to the performance of a layered feedforward network to which image features extracted by the method of moments are presented as input.< >
ISSN:1045-9227
1941-0093
DOI:10.1109/72.125865