Invariant pattern recognition with higher-order neural networks
Translation, rotation (in plane) and scale invariant pattern recognition is a high-order recognition problem encountered frequently in real-world applications. But neither traditional image process/pattern recognition algorithms nor artificial neural networks have yet provided satisfactory solution...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Theses and Dissertations |
Published: |
2008
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/4359 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
id |
sg-ntu-dr.10356-4359 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-43592023-07-04T15:12:17Z Invariant pattern recognition with higher-order neural networks He, Zhengquan. Mohammed Yakoob Siyal School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Translation, rotation (in plane) and scale invariant pattern recognition is a high-order recognition problem encountered frequently in real-world applications. But neither traditional image process/pattern recognition algorithms nor artificial neural networks have yet provided satisfactory solutions for this problem after years of study. Recent research has shown that a higher order neural networks (HONNs) of order three with built-in invariances can effectively achieve invariant pattern recognition. Master of Engineering 2008-09-17T09:49:59Z 2008-09-17T09:49:59Z 1999 1999 Thesis http://hdl.handle.net/10356/4359 Nanyang Technological University application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
topic |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems |
spellingShingle |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems He, Zhengquan. Invariant pattern recognition with higher-order neural networks |
description |
Translation, rotation (in plane) and scale invariant pattern recognition is a high-order recognition problem encountered frequently in real-world applications. But neither traditional image process/pattern recognition algorithms nor artificial neural
networks have yet provided satisfactory solutions for this problem after years of study. Recent research has shown that a higher order neural networks (HONNs) of order three with built-in invariances can effectively achieve invariant pattern recognition. |
author2 |
Mohammed Yakoob Siyal |
author_facet |
Mohammed Yakoob Siyal He, Zhengquan. |
format |
Theses and Dissertations |
author |
He, Zhengquan. |
author_sort |
He, Zhengquan. |
title |
Invariant pattern recognition with higher-order neural networks |
title_short |
Invariant pattern recognition with higher-order neural networks |
title_full |
Invariant pattern recognition with higher-order neural networks |
title_fullStr |
Invariant pattern recognition with higher-order neural networks |
title_full_unstemmed |
Invariant pattern recognition with higher-order neural networks |
title_sort |
invariant pattern recognition with higher-order neural networks |
publishDate |
2008 |
url |
http://hdl.handle.net/10356/4359 |
_version_ |
1772825773155024896 |