TGV methodology MATLAB implementation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F22%3APR36443" target="_blank" >RIV/00216305:26210/22:PR36443 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0141938222001044#mmc1" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0141938222001044#mmc1</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

TGV methodology MATLAB implementation

Popis výsledku v původním jazyce

n implementation of TGV methodology published in TGV searches for an optimal setting of a computer vision system or of its sub-system. Within the system/sub-system must be implemented a weighted means grayscale conversion method. This implementation of TGV is based on one-stage grid-search algorithm supervised by a computer vision expert. The expert assesses settings proposed by the grid-searc method using WECIA graphs. One WECIA graph displays dependence of the system performance on setting of the grayscale conversion weights for one specific setting of the remaining adjustable parameters of the system/sub-system. The performance of the system/sub-system can be evaluated using one or more objective functions where only one of these function is used as a primary objective function, i.e. the grid-search algorihm uses this function for the selection of the optimal parameter setting. The expert can use all the objective functions while assessing a setting proposed by the grid-search algorithm, i.e. nJ WECIA graph are displeyed for one assesed setting where nJ is the number of the objective functions.

Název v anglickém jazyce

TGV methodology MATLAB implementation

Popis výsledku anglicky

n implementation of TGV methodology published in TGV searches for an optimal setting of a computer vision system or of its sub-system. Within the system/sub-system must be implemented a weighted means grayscale conversion method. This implementation of TGV is based on one-stage grid-search algorithm supervised by a computer vision expert. The expert assesses settings proposed by the grid-searc method using WECIA graphs. One WECIA graph displays dependence of the system performance on setting of the grayscale conversion weights for one specific setting of the remaining adjustable parameters of the system/sub-system. The performance of the system/sub-system can be evaluated using one or more objective functions where only one of these function is used as a primary objective function, i.e. the grid-search algorihm uses this function for the selection of the optimal parameter setting. The expert can use all the objective functions while assessing a setting proposed by the grid-search algorithm, i.e. nJ WECIA graph are displeyed for one assesed setting where nJ is the number of the objective functions.

Druh

R - Software

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LTC18053" target="_blank" >LTC18053: Pokročilé metody Nature-Inspired optimalizačních algoritmů a HPC implementace pro řešení reálných aplikací</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Interní identifikační kód produktu

TGV

Technické parametry

freeware

Ekonomické parametry

Not applicable

IČO vlastníka výsledku

00216305

Název vlastníka

Vysoké učení technické v Brně