Transfer Learning of Mixture Texture Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F20%3A00535433" target="_blank" >RIV/67985556:_____/20:00535433 - isvavai.cz</a>

Alternative codes found

RIV/61384399:31160/20:00056427

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-030-63007-2_65" target="_blank" >http://dx.doi.org/10.1007/978-3-030-63007-2_65</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-63007-2_65" target="_blank" >10.1007/978-3-030-63007-2_65</a>

Result language

angličtina

Original language name

Transfer Learning of Mixture Texture Models

Original language description

A transfer learning approach for multidimensional parametric mixture random field-based textural representation is introduced. The proposed transfer learning approach allows alleviating the multidimensional mixture models requirement for sufficiently large, but not always available, learning data sets. These compound random field models consist of an underlying structure model that controls transitions between several sub-models, each of them has different characteristics. The structure model proposed is a two-dimensional probabilistic mixture model, either of the Bernoulli or Gaussian mixture type. Local textures are modeled using the fully multispectral three-dimensional Gaussian mixture sub-models. Both presented compound random field models allow the reproduction of, compresses, edits, and enlarges a given measured color, multispectral, or bidirectional texture function (BTF) texture so that ideally, both measured and synthetic textures are visually indiscernible.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

20205 - Automation and control systems

Project

<a href="/en/project/GA19-12340S" target="_blank" >GA19-12340S: Surface material recognition under variable optical observation conditions</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2020

Confidentiality

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

Article name in the collection

Computational Collective Intelligence

ISBN

978-3-030-63006-5

ISSN

0302-9743

e-ISSN

1611-3349

Number of pages

13

Pages from-to

825-837

Publisher name

Springer Nature Switzerland AG

Place of publication

Cham

Event location

Da Nang

Event date

Nov 30, 2020

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—