Non-parametric texture synthesis using texture classification

© 2017, Society for Imaging Science and Technology. In this paper we present a method of texture synthesis which removes the need for users to set, or even understand, parameters which have an impact on the synthesized output. We accomplish this by first classifying each input texture sample into on...

Full description

Bibliographic Details
Main Authors: Ziga, K., Bagchi, J., Allebach, J., Zhu, Maggie
Format: Conference Paper
Published: 2017
Online Access:http://hdl.handle.net/20.500.11937/69664
_version_ 1848762101005287424
author Ziga, K.
Bagchi, J.
Allebach, J.
Zhu, Maggie
author_facet Ziga, K.
Bagchi, J.
Allebach, J.
Zhu, Maggie
author_sort Ziga, K.
building Curtin Institutional Repository
collection Online Access
description © 2017, Society for Imaging Science and Technology. In this paper we present a method of texture synthesis which removes the need for users to set, or even understand, parameters which have an impact on the synthesized output. We accomplish this by first classifying each input texture sample into one of three texture types: regular, irregular and stochastic. We found that textures within a class were synthesized well with similar parameters. If we know the input texture class, we can provide a good starting set of parameters for the synthesis algorithm. Instead of requiring a user to manually select a set of parameters, we simply ask that the user tell us whether the synthesized texture is satisfactory or not. If the output is not satisfactory, we adjust parameters and try again until the user is happy with the output. In this implementation we use the image quilting method in [1], a texture synthesis algorithm, as well as texture classification. With small adjustments our method can be applied to other texture synthesis methods.
first_indexed 2025-11-14T10:42:12Z
format Conference Paper
id curtin-20.500.11937-69664
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:42:12Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-696642018-08-08T04:57:20Z Non-parametric texture synthesis using texture classification Ziga, K. Bagchi, J. Allebach, J. Zhu, Maggie © 2017, Society for Imaging Science and Technology. In this paper we present a method of texture synthesis which removes the need for users to set, or even understand, parameters which have an impact on the synthesized output. We accomplish this by first classifying each input texture sample into one of three texture types: regular, irregular and stochastic. We found that textures within a class were synthesized well with similar parameters. If we know the input texture class, we can provide a good starting set of parameters for the synthesis algorithm. Instead of requiring a user to manually select a set of parameters, we simply ask that the user tell us whether the synthesized texture is satisfactory or not. If the output is not satisfactory, we adjust parameters and try again until the user is happy with the output. In this implementation we use the image quilting method in [1], a texture synthesis algorithm, as well as texture classification. With small adjustments our method can be applied to other texture synthesis methods. 2017 Conference Paper http://hdl.handle.net/20.500.11937/69664 10.2352/ISSN.2470-1173.2017.17.COIMG-436 restricted
spellingShingle Ziga, K.
Bagchi, J.
Allebach, J.
Zhu, Maggie
Non-parametric texture synthesis using texture classification
title Non-parametric texture synthesis using texture classification
title_full Non-parametric texture synthesis using texture classification
title_fullStr Non-parametric texture synthesis using texture classification
title_full_unstemmed Non-parametric texture synthesis using texture classification
title_short Non-parametric texture synthesis using texture classification
title_sort non-parametric texture synthesis using texture classification
url http://hdl.handle.net/20.500.11937/69664