Magnocellular Pathway for Rotation Invariant Neocognitron
Publication Type
Journal Article
Publication Date
1993
Abstract
In the mammalian visual system, magnocellular pathway and parvocellular pathway cooperatively process visual information in parallel. The magnocellular pathway is more global and less particular about the details while the parvocellular pathway recognizes objects based on the local features. In many aspects, Neocognitron may be regarded as the artificial analogue of the parvocellular pathway. It is interesting then to model the magnocellular pathway. In order to achieve rotation invariance for Neocognitron, we propose a neural network model after the magnocellular pathway and expand its roles to include surmising the orientation of the input pattern prior to recognition. With the incorporation of the magnocellular pathway, a basic shift in the original paradigm has taken place. A pattern is now said to be recognized when and only when one of the winners of the magnocellular pathway is validified by the parvocellular pathway. We have implemented the magnocellular pathway coupled with Neocognitron parallel on transputers; our simulation programme is now able to recognize numerals in arbitrary orientation.
Discipline
Business
Research Areas
Organisational Behaviour and Human Resources
Publication
International Journal of Neural Systems
Volume
4
Issue
1
First Page
43
Last Page
54
ISSN
0129-0657
Identifier
10.1142/S0129065793000067
Citation
TING, Hian Ann, Christopher.
Magnocellular Pathway for Rotation Invariant Neocognitron. (1993). International Journal of Neural Systems. 4, (1), 43-54.
Available at: https://ink.library.smu.edu.sg/lkcsb_research/775
Additional URL
https://doi.org/10.1142/S0129065793000067