Feature-preserving procedural texture

Hyeong Yeop Kang; Junghyun Han

doi:10.1007/s00371-017-1375-8

Feature-preserving procedural texture

Hyeong Yeop Kang, Junghyun Han

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

This paper presents how to synthesize a texture in a procedural way that preserves the features of the input exemplar. The exemplar is analyzed in both spatial and frequency domains to be decomposed into feature and non-feature parts. Then, the non-feature parts are reproduced as a procedural noise, whereas the features are independently synthesized. They are combined to output a non-repetitive texture that also preserves the exemplar’s features. The proposed method allows the user to control the extent of extracted features and also enables a texture to edited quite effectively.

Original language	English
Pages (from-to)	761-768
Number of pages	8
Journal	Visual Computer
Volume	33
Issue number	6-8
DOIs	https://doi.org/10.1007/s00371-017-1375-8
Publication status	Published - 2017 Jun 1

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIP) (No. NRF-2016R1A2B3014319) and by Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea government (MSIP) (No. R0115-16-1011).

Publisher Copyright:
© 2017, Springer-Verlag Berlin Heidelberg.

Keywords

Feature preservation
Noise by example
Procedural texturing
Texture analysis

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computer Graphics and Computer-Aided Design

Access to Document

10.1007/s00371-017-1375-8

Cite this

@article{ccb6808a768a42819ec7619d15537968,

title = "Feature-preserving procedural texture",

abstract = "This paper presents how to synthesize a texture in a procedural way that preserves the features of the input exemplar. The exemplar is analyzed in both spatial and frequency domains to be decomposed into feature and non-feature parts. Then, the non-feature parts are reproduced as a procedural noise, whereas the features are independently synthesized. They are combined to output a non-repetitive texture that also preserves the exemplar{\textquoteright}s features. The proposed method allows the user to control the extent of extracted features and also enables a texture to edited quite effectively.",

keywords = "Feature preservation, Noise by example, Procedural texturing, Texture analysis",

author = "Kang, {Hyeong Yeop} and Junghyun Han",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIP) (No. NRF-2016R1A2B3014319) and by Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea government (MSIP) (No. R0115-16-1011). Publisher Copyright: {\textcopyright} 2017, Springer-Verlag Berlin Heidelberg.",

year = "2017",

month = jun,

day = "1",

doi = "10.1007/s00371-017-1375-8",

language = "English",

volume = "33",

pages = "761--768",

journal = "Visual Computer",

issn = "0178-2789",

publisher = "Springer Verlag",

number = "6-8",

}

TY - JOUR

T1 - Feature-preserving procedural texture

AU - Kang, Hyeong Yeop

AU - Han, Junghyun

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIP) (No. NRF-2016R1A2B3014319) and by Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea government (MSIP) (No. R0115-16-1011). Publisher Copyright: © 2017, Springer-Verlag Berlin Heidelberg.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - This paper presents how to synthesize a texture in a procedural way that preserves the features of the input exemplar. The exemplar is analyzed in both spatial and frequency domains to be decomposed into feature and non-feature parts. Then, the non-feature parts are reproduced as a procedural noise, whereas the features are independently synthesized. They are combined to output a non-repetitive texture that also preserves the exemplar’s features. The proposed method allows the user to control the extent of extracted features and also enables a texture to edited quite effectively.

AB - This paper presents how to synthesize a texture in a procedural way that preserves the features of the input exemplar. The exemplar is analyzed in both spatial and frequency domains to be decomposed into feature and non-feature parts. Then, the non-feature parts are reproduced as a procedural noise, whereas the features are independently synthesized. They are combined to output a non-repetitive texture that also preserves the exemplar’s features. The proposed method allows the user to control the extent of extracted features and also enables a texture to edited quite effectively.

KW - Feature preservation

KW - Noise by example

KW - Procedural texturing

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=85018749189&partnerID=8YFLogxK

U2 - 10.1007/s00371-017-1375-8

DO - 10.1007/s00371-017-1375-8

M3 - Article

AN - SCOPUS:85018749189

SN - 0178-2789

VL - 33

SP - 761

EP - 768

JO - Visual Computer

JF - Visual Computer

IS - 6-8

ER -

Feature-preserving procedural texture

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this