Filter Selection for the Design of Image Matrix

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F00%3A43500010" target="_blank" >RIV/00216305:26220/00:43500010 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Filter Selection for the Design of Image Matrix

Original language description

A real technological scene was simulated by digitizing two-dimensional pictures of real objects. The ART network gave relatively good results. Its application is suitable especialy for the recognition of not very damaged and noisy pictures and in the case when other patterns are added to the learned network. The Kohonen network presented excellent results. The learning went off very quickly and that is why Kohonen network is suitable for applications where the patterns are often changed. The back-propagation algorithm yielded excellent results too. The learning of this network took a longer time than of the Kohonen one but the results of the damaged pattern recognition were better.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2000

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

CD Proceedings of the International Conference on Signal Processing Aplications&Technology.

ISBN

—

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

—

Publisher name

CMP Media Inc. USA

Place of publication

Dallas (USA)

Event location

—

Event date

—

Type of event by nationality

—

UT code for WoS article

—