Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 7, 2026

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

Rotation-invariant neural pattern recognition system with application to coin recognition.

M Fukumi¹, S Omatu, F Takeda

¹Fac. of Eng., Tokushima Univ.

IEEE Transactions on Neural Networks

|January 1, 1992

Summary

A novel neural network system achieves rotation-invariant pattern recognition. This approach effectively distinguishes between similarly shaped objects, like coins, regardless of their orientation.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Molecular Identification and Classification of Strawberry Phylloid Fruit Phytoplasma in Group 16SrI, New Subgroup.

Plant disease·2019

Same author

Gastric secretory and hormonal patterns in end-stage chagasic achalasia.

Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus·2009

Same author

[Multiple recurrent cardiac myxomas].

Kyobu geka. The Japanese journal of thoracic surgery·2009

Same author

VEP optimal channel selection using genetic algorithm for neural network classification of alcoholics.

IEEE transactions on neural networks·2008

Same author

A grid computing infrastructure for MEG data analysis.

Neurology & clinical neurophysiology : NCN·2005

Same author

Postsynaptic and extrasynaptic localization of Kv4.2 channels in the mouse hippocampal region, with special reference to targeted clustering at gabaergic synapses.

Neuroscience·2005

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Pattern recognition often requires classifying transformed patterns.
Handling variations like rotation is a significant challenge in real-world applications.

Purpose of the Study:

To propose a neural pattern recognition system that is insensitive to input pattern rotation.
To develop a method for robust pattern classification under varying orientations.

Main Methods:

A system combining a fixed invariance network with multiple slabs and a trainable multilayered network was designed.
The system was applied to a specific coin recognition task involving 500 yen and 500 won coins.

Main Results:

The proposed system demonstrated effectiveness in a rotation-invariant coin recognition task.

Related Experiment Videos

Last Updated: Jul 7, 2026

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

Published on: February 23, 2024

Successful distinction between the two types of coins was achieved despite rotational variations.

Conclusions:

The developed neural network architecture provides a viable solution for rotation-invariant pattern recognition.
The approach shows promise for applications requiring classification of patterns with arbitrary rotations.