Zpracování obrazu a videa pro hodnocení obrazové kvality s použitím neuronových sítí

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A03117879" target="_blank" >RIV/68407700:21230/06:03117879 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Image and Video Processing for Image Quality Evaluation Using Artificial Neural Network

Popis výsledku v původním jazyce

A novel approach for objective image quality assessment is presented in this paper. Reliable methods are often required to evaluate the quality effects of the visual artifacts appearing in a digital image processing while using lossy image compression. Optimization of the previously proposed model for image quality evaluation with Artificial Neural Network (ANN) has been done. The main aim of this approach is to automatically derive a score that is the same as, or at least well correlated with the MeanOpinion Score (MOS) obtained from the subjective votes of many observers. Advanced method of data preprocessing (Mutual Information - MI and Principal Component Analysis - PCA) has been applied to obtain good prediction of the image quality which is close to subjective results from the group of observers - Mean Opinion Scores (MOS). The proposed model achieves good prediction performance for used test samples.

Název v anglickém jazyce

Image and Video Processing for Image Quality Evaluation Using Artificial Neural Network

Popis výsledku anglicky

A novel approach for objective image quality assessment is presented in this paper. Reliable methods are often required to evaluate the quality effects of the visual artifacts appearing in a digital image processing while using lossy image compression. Optimization of the previously proposed model for image quality evaluation with Artificial Neural Network (ANN) has been done. The main aim of this approach is to automatically derive a score that is the same as, or at least well correlated with the MeanOpinion Score (MOS) obtained from the subjective votes of many observers. Advanced method of data preprocessing (Mutual Information - MI and Principal Component Analysis - PCA) has been applied to obtain good prediction of the image quality which is close to subjective results from the group of observers - Mean Opinion Scores (MOS). The proposed model achieves good prediction performance for used test samples.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2006

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Workshop 2006

ISBN

80-01-03439-9

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

—

Název nakladatele

ČVUT

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

20. 2. 2006

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—