DocumentCode :
910494
Title :
Shift invariant neural net for machine vision
Author :
Elliman, D.G. ; Banks, R.N.
Author_Institution :
Dept. of Comput. Sci., Nottingham Univ., UK
Volume :
137
Issue :
3
fYear :
1990
fDate :
6/1/1990 12:00:00 AM
Firstpage :
183
Lastpage :
187
Abstract :
A multilayer network is described which is able to recognise simple shapes in a shift, size, and rotation invariant manner. The use of layers of units to smooth and then to shift the image eliminates the need for the very large numbers of cells which are often proposed in shift invariant networks. The network was trained using back-propagation and is not intended to be plausible as a model of biological vision at the level of cell and connection detail. Some interesting parallels with human vision are noted in the emergent behaviour of the network.<>
Keywords :
computer vision; neural nets; pattern recognition; picture processing; back-propagation; human vision; image processing; image shifting; machine vision; multilayer network; rotational invariance; shift independence; shift invariant neural net;
fLanguage :
English
Journal_Title :
Communications, Speech and Vision, IEE Proceedings I
Publisher :
iet
ISSN :
0956-3776
Type :
jour
Filename :
218060
Link To Document :
بازگشت