Dynamic Texture Similarity Criterion

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F18%3A00321888" target="_blank" >RIV/68407700:21240/18:00321888 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.icpr2018.org/" target="_blank" >http://www.icpr2018.org/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICPR.2018.8545370" target="_blank" >10.1109/ICPR.2018.8545370</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Dynamic Texture Similarity Criterion

Popis výsledku v původním jazyce

Evaluating the likeness of two similar dynamic textures or dynamic textures of the same type is still a challenging and unresolved problem. Temporal dimension and dynamics in texture complicates the problem of mere texture similarities and makes it even more challenging. A simple approach to compute difference between DTs bag of features, STSIM of pure statistisc methods are insufficient and does not affect the variable texture dynamics which is crucial for human recognition. Testing the similarity, quality and fidelity of both natural and arftificial dynamic textures is a problem that can be solved by psychometric tests with users, but these are challenging both in terms of time, human resources and data processing. The solution provided by us compares the frequency and regularity of the time behavior of spatial frequencies in texture with great consistency with the values provided by users testing. The solution itself provides a functional metric that can be used to evaluate the similarity of textures modified by inpainting, retouching as well as evaluating the similarity of the dynamics across the type of the DTs.

Název v anglickém jazyce

Dynamic Texture Similarity Criterion

Popis výsledku anglicky

Evaluating the likeness of two similar dynamic textures or dynamic textures of the same type is still a challenging and unresolved problem. Temporal dimension and dynamics in texture complicates the problem of mere texture similarities and makes it even more challenging. A simple approach to compute difference between DTs bag of features, STSIM of pure statistisc methods are insufficient and does not affect the variable texture dynamics which is crucial for human recognition. Testing the similarity, quality and fidelity of both natural and arftificial dynamic textures is a problem that can be solved by psychometric tests with users, but these are challenging both in terms of time, human resources and data processing. The solution provided by us compares the frequency and regularity of the time behavior of spatial frequencies in texture with great consistency with the values provided by users testing. The solution itself provides a functional metric that can be used to evaluate the similarity of textures modified by inpainting, retouching as well as evaluating the similarity of the dynamics across the type of the DTs.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

2018 24rd International Conference on Pattern Recognition (ICPR)

ISBN

978-1-5386-3788-3

ISSN

—

e-ISSN

1051-4651

Počet stran výsledku

6

Strana od-do

904-909

Název nakladatele

IEEE

Místo vydání

Piscataway, NJ

Místo konání akce

Beijing

Datum konání akce

20. 8. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000455146800151