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...
Saved in:
Main Authors: | Maul, T., Baba, S., Yusof, A. |
---|---|
Format: | Article |
Published: |
2005
|
Subjects: | |
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!
|
Similar Items
-
Conjunctions in biological neural architectures for visual pose estimation / Tom´As Maul
by: Tom´As, Maul
Published: (2006) -
Unsupervised learning in second-order neural networks for motion analysis
by: Maul, Tomas, et al.
Published: (2011) -
Experimental analysis of permanent magnet attraction force on ferromagnetic plate
by: Chee, Ka Fei
Published: (2024) -
On analysis of Invariant Characteristic for Moment Invariant Techniques
by: Shahrul Nizam Yaakob, et al.
Published: (2008) -
Invariant domain based watermarking using Riesz Transform
by: Abbasi, A.
Published: (2014)