Neural network approach in image analysis of comlex systems

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13430%2F00%3A00000547" target="_blank" >RIV/44555601:13430/00:00000547 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Neural network approach in image analysis of comlex systems

Original language description

In the process of image analysis of complex systems consisting of large number of objects - typical for astronomy, thin film physics, biology, etc. - the reliable and accurate detection of both the size and spatial distribution of objects is very important. This contribution reviews the new approaches based on the neural network approach. The neural network approach is evaluated in terms of their performance and simplicity of their implementation. As a part of the development of the neural network approach a simple algorithm describing the spatial distribution of objects in the image is presented. While the new approach is tested on simulated hard-disk models, the results can be applied to the experimentally derived microphotographs of discontinuous and composite metal films.

Czech name

—

Czech description

—

Type

A - Audiovisual production

CEP classification

BM - Solid-state physics and magnetism

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

ISBN

—

Place of publication

Pula

Publisher/client name

Croatian Vacuum Society

Version

—

Carrier ID

—