Stippling by example

Sung Ye Kim, Ross Maciejewski, Tobias Isenberg, William M. Andrews, Wei Chen, Mario Costa Sousa, David S. Ebert

Research output: Chapter in Book/Report/Conference proceedingConference contribution

40 Citations (Scopus)

Abstract

In this work, we focus on stippling as an artistic style and discuss our technique for capturing and reproducing stipple features unique to an individual artist. We employ a texture synthesis algorithm based on the gray-level co-occurrence matrix (GLCM) of a texture field. This algorithm uses a texture similarity metric to generate stipple textures that are perceptually similar to input samples, allowing us to better capture and reproduce stipple distributions.First, we extract example stipple textures representing various tones in order to create an approximate tone map used by the artist. Second, we extract the stipple marks and distributions from the extracted example textures, generating both a lookup table of stipple marks and a texture representing the stipple distribution. Third, we use the distribution of stipples to synthesize similar distributions with slight variations using a numerical measure of the error between the synthesized texture and the example texture as the basis for replication. Finally, we apply the synthesized stipple distribution to a 2D grayscale image and place stipple marks onto the distribution, thereby creating a stippled image that is statistically similar to images created by the example artist.

Original languageEnglish (US)
Title of host publicationNPAR Symposium on Non-Photorealistic Animation and Rendering
Pages41-50
Number of pages10
DOIs
StatePublished - 2009
Externally publishedYes
EventNPAR 2009: The 7th International Symposium on Non-Photorealistic Animation and Rendering - New Orleans, LA, United States
Duration: Aug 1 2009Aug 2 2009

Other

OtherNPAR 2009: The 7th International Symposium on Non-Photorealistic Animation and Rendering
CountryUnited States
CityNew Orleans, LA
Period8/1/098/2/09

Fingerprint

Texture
Textures
Gray Level Co-occurrence Matrix
Texture Synthesis
Look-up Table
Table lookup
Replication
Metric

Keywords

  • Computer-generated stippling
  • Statistical similarity
  • Stipple mark distribution
  • Stippling by example
  • Texture analysis and synthesis

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Modeling and Simulation

Cite this

Kim, S. Y., Maciejewski, R., Isenberg, T., Andrews, W. M., Chen, W., Sousa, M. C., & Ebert, D. S. (2009). Stippling by example. In NPAR Symposium on Non-Photorealistic Animation and Rendering (pp. 41-50) https://doi.org/10.1145/1572614.1572622

Stippling by example. / Kim, Sung Ye; Maciejewski, Ross; Isenberg, Tobias; Andrews, William M.; Chen, Wei; Sousa, Mario Costa; Ebert, David S.

NPAR Symposium on Non-Photorealistic Animation and Rendering. 2009. p. 41-50.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, SY, Maciejewski, R, Isenberg, T, Andrews, WM, Chen, W, Sousa, MC & Ebert, DS 2009, Stippling by example. in NPAR Symposium on Non-Photorealistic Animation and Rendering. pp. 41-50, NPAR 2009: The 7th International Symposium on Non-Photorealistic Animation and Rendering, New Orleans, LA, United States, 8/1/09. https://doi.org/10.1145/1572614.1572622
Kim SY, Maciejewski R, Isenberg T, Andrews WM, Chen W, Sousa MC et al. Stippling by example. In NPAR Symposium on Non-Photorealistic Animation and Rendering. 2009. p. 41-50 https://doi.org/10.1145/1572614.1572622
Kim, Sung Ye ; Maciejewski, Ross ; Isenberg, Tobias ; Andrews, William M. ; Chen, Wei ; Sousa, Mario Costa ; Ebert, David S. / Stippling by example. NPAR Symposium on Non-Photorealistic Animation and Rendering. 2009. pp. 41-50
@inproceedings{018003bde20145e98b2319c9be7afc70,
title = "Stippling by example",
abstract = "In this work, we focus on stippling as an artistic style and discuss our technique for capturing and reproducing stipple features unique to an individual artist. We employ a texture synthesis algorithm based on the gray-level co-occurrence matrix (GLCM) of a texture field. This algorithm uses a texture similarity metric to generate stipple textures that are perceptually similar to input samples, allowing us to better capture and reproduce stipple distributions.First, we extract example stipple textures representing various tones in order to create an approximate tone map used by the artist. Second, we extract the stipple marks and distributions from the extracted example textures, generating both a lookup table of stipple marks and a texture representing the stipple distribution. Third, we use the distribution of stipples to synthesize similar distributions with slight variations using a numerical measure of the error between the synthesized texture and the example texture as the basis for replication. Finally, we apply the synthesized stipple distribution to a 2D grayscale image and place stipple marks onto the distribution, thereby creating a stippled image that is statistically similar to images created by the example artist.",
keywords = "Computer-generated stippling, Statistical similarity, Stipple mark distribution, Stippling by example, Texture analysis and synthesis",
author = "Kim, {Sung Ye} and Ross Maciejewski and Tobias Isenberg and Andrews, {William M.} and Wei Chen and Sousa, {Mario Costa} and Ebert, {David S.}",
year = "2009",
doi = "10.1145/1572614.1572622",
language = "English (US)",
isbn = "9781605586045",
pages = "41--50",
booktitle = "NPAR Symposium on Non-Photorealistic Animation and Rendering",

}

TY - GEN

T1 - Stippling by example

AU - Kim, Sung Ye

AU - Maciejewski, Ross

AU - Isenberg, Tobias

AU - Andrews, William M.

AU - Chen, Wei

AU - Sousa, Mario Costa

AU - Ebert, David S.

PY - 2009

Y1 - 2009

N2 - In this work, we focus on stippling as an artistic style and discuss our technique for capturing and reproducing stipple features unique to an individual artist. We employ a texture synthesis algorithm based on the gray-level co-occurrence matrix (GLCM) of a texture field. This algorithm uses a texture similarity metric to generate stipple textures that are perceptually similar to input samples, allowing us to better capture and reproduce stipple distributions.First, we extract example stipple textures representing various tones in order to create an approximate tone map used by the artist. Second, we extract the stipple marks and distributions from the extracted example textures, generating both a lookup table of stipple marks and a texture representing the stipple distribution. Third, we use the distribution of stipples to synthesize similar distributions with slight variations using a numerical measure of the error between the synthesized texture and the example texture as the basis for replication. Finally, we apply the synthesized stipple distribution to a 2D grayscale image and place stipple marks onto the distribution, thereby creating a stippled image that is statistically similar to images created by the example artist.

AB - In this work, we focus on stippling as an artistic style and discuss our technique for capturing and reproducing stipple features unique to an individual artist. We employ a texture synthesis algorithm based on the gray-level co-occurrence matrix (GLCM) of a texture field. This algorithm uses a texture similarity metric to generate stipple textures that are perceptually similar to input samples, allowing us to better capture and reproduce stipple distributions.First, we extract example stipple textures representing various tones in order to create an approximate tone map used by the artist. Second, we extract the stipple marks and distributions from the extracted example textures, generating both a lookup table of stipple marks and a texture representing the stipple distribution. Third, we use the distribution of stipples to synthesize similar distributions with slight variations using a numerical measure of the error between the synthesized texture and the example texture as the basis for replication. Finally, we apply the synthesized stipple distribution to a 2D grayscale image and place stipple marks onto the distribution, thereby creating a stippled image that is statistically similar to images created by the example artist.

KW - Computer-generated stippling

KW - Statistical similarity

KW - Stipple mark distribution

KW - Stippling by example

KW - Texture analysis and synthesis

UR - http://www.scopus.com/inward/record.url?scp=70450194566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450194566&partnerID=8YFLogxK

U2 - 10.1145/1572614.1572622

DO - 10.1145/1572614.1572622

M3 - Conference contribution

AN - SCOPUS:70450194566

SN - 9781605586045

SP - 41

EP - 50

BT - NPAR Symposium on Non-Photorealistic Animation and Rendering

ER -