Cover Image

Dynamic inputs and attraction force analysis for visual invariance and transformation estimation

This paper aims to tackle two fundamental problems faced by multiple object recognition systems: invariance and transformation estimation. A neural normalization approach is adopted, which allows for the subsequent incorporation of invariant features. Two new approaches are introduced: dynamic input...

Full description

Saved in:
Bibliographic Details
Main Authors: Maul, T., Baba, S., Yusof, A.
Format: Article
Published: 2005
Subjects:
T Technology (General)
Online Access:http://eprints.um.edu.my/5688/
http://link.springer.com/chapter/10.1007%2F11539087_120?LI=true#page-1
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.5688
record_format eprints
spelling my.um.eprints.56882013-01-04T16:08:11Z http://eprints.um.edu.my/5688/ Dynamic inputs and attraction force analysis for visual invariance and transformation estimation Maul, T. Baba, S. Yusof, A. T Technology (General) This paper aims to tackle two fundamental problems faced by multiple object recognition systems: invariance and transformation estimation. A neural normalization approach is adopted, which allows for the subsequent incorporation of invariant features. Two new approaches are introduced: dynamic inputs (DI) and attraction force analysis (AFA). The DI concept refers to a cloud of inputs that is allowed to change its configuration in order to latch onto objects thus creating object-based reference frames. AFA is used in order to provide clouds with transformation estimations thus maximizing the efficiency with which they can latch onto objects. AFA analyzes the length and angular properties of the correspondences that are found between stored-patterns and the information conveyed by clouds. The solution provides significant invariance and useful estimations pertaining to translation, scale, rotation and combinations of these. The estimations provided are also considerably resistant to other factors such as deformation, noise, occlusion and clutter. 2005 Article PeerReviewed Maul, T. and Baba, S. and Yusof, A. (2005) Dynamic inputs and attraction force analysis for visual invariance and transformation estimation. Advances in Natural Computation. pp. 407-408. http://link.springer.com/chapter/10.1007%2F11539087_120?LI=true#page-1
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic T Technology (General)
spellingShingle T Technology (General)
Maul, T.
Baba, S.
Yusof, A.
Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
description This paper aims to tackle two fundamental problems faced by multiple object recognition systems: invariance and transformation estimation. A neural normalization approach is adopted, which allows for the subsequent incorporation of invariant features. Two new approaches are introduced: dynamic inputs (DI) and attraction force analysis (AFA). The DI concept refers to a cloud of inputs that is allowed to change its configuration in order to latch onto objects thus creating object-based reference frames. AFA is used in order to provide clouds with transformation estimations thus maximizing the efficiency with which they can latch onto objects. AFA analyzes the length and angular properties of the correspondences that are found between stored-patterns and the information conveyed by clouds. The solution provides significant invariance and useful estimations pertaining to translation, scale, rotation and combinations of these. The estimations provided are also considerably resistant to other factors such as deformation, noise, occlusion and clutter.
format Article
author Maul, T.
Baba, S.
Yusof, A.
author_facet Maul, T.
Baba, S.
Yusof, A.
author_sort Maul, T.
title Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
title_short Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
title_full Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
title_fullStr Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
title_full_unstemmed Dynamic inputs and attraction force analysis for visual invariance and transformation estimation
title_sort dynamic inputs and attraction force analysis for visual invariance and transformation estimation
publishDate 2005
url http://eprints.um.edu.my/5688/
http://link.springer.com/chapter/10.1007%2F11539087_120?LI=true#page-1
_version_ 1643687642757332992
score 13.211869

Similar Items