Share Email Print
cover

Proceedings Paper

Neural-like model of artificial vision for pattern analysis
Author(s): Alexander V. Pavlov
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Model of Artificial Vision is discussed. The task is to find the part of reference pattern that presents in the object image. Condition is the task has to be solved in the framework of the Classifical Approach to the image understanding, i.e. without formal description of patterns. In two-layered bidirectional optical neural network image layer as a comparison layer is realized. Function of selective attention as filtering function in the correlation layer is involved. Energy function for the NN is defined as scalar product of object image and formed by NN expectation.

Paper Details

Date Published: 1 April 1998
PDF: 7 pages
Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304954
Show Author Affiliations
Alexander V. Pavlov, S.I. Vavilov State Optical Institute (Russia)


Published in SPIE Proceedings Vol. 3402:
Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks

© SPIE. Terms of Use
Back to Top