Expressive line selection by example

Eric B. Lum, Kwan-Liu Ma

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

An important problem in computer generated line drawing is determining which set of lines produces a representation that is in agreement with a user's communication goals. We describe a method that enables a user to intuitively specify which types of lines should appear in rendered images. Our method employs conventional silhouette-edge and other feature-line extraction algorithms to derive a set of candidate lines, and integrates machine learning into a user-directed line removal process using a sketching metaphor. The method features a simple and intuitive user interface that provides interactive control over the resulting line selection criteria and can be easily adapted to work in conjunction with existing line detection and rendering algorithms. Much of the method's power comes from its ability to learn the relationships between numerous geometric attributes that define a line style. Once learned, a user's style and intent can be passed from object to object as well as from view to view.

Original languageEnglish (US)
Pages (from-to)811-820
Number of pages10
JournalVisual Computer
Volume21
Issue number8-10
DOIs
StatePublished - Sep 1 2005

Fingerprint

User interfaces
Learning systems
Communication
user interface
metaphor
candidacy
communication
ability
learning

Keywords

  • Example-based rendering
  • Machine learning
  • Non-photorealistic rendering
  • Silhouettes

ASJC Scopus subject areas

  • Software
  • Education
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Expressive line selection by example. / Lum, Eric B.; Ma, Kwan-Liu.

In: Visual Computer, Vol. 21, No. 8-10, 01.09.2005, p. 811-820.

Research output: Contribution to journalArticle

Lum, Eric B. ; Ma, Kwan-Liu. / Expressive line selection by example. In: Visual Computer. 2005 ; Vol. 21, No. 8-10. pp. 811-820.
@article{66a3f3bcc8f7466d9fc7e34ef04f095c,
title = "Expressive line selection by example",
abstract = "An important problem in computer generated line drawing is determining which set of lines produces a representation that is in agreement with a user's communication goals. We describe a method that enables a user to intuitively specify which types of lines should appear in rendered images. Our method employs conventional silhouette-edge and other feature-line extraction algorithms to derive a set of candidate lines, and integrates machine learning into a user-directed line removal process using a sketching metaphor. The method features a simple and intuitive user interface that provides interactive control over the resulting line selection criteria and can be easily adapted to work in conjunction with existing line detection and rendering algorithms. Much of the method's power comes from its ability to learn the relationships between numerous geometric attributes that define a line style. Once learned, a user's style and intent can be passed from object to object as well as from view to view.",
keywords = "Example-based rendering, Machine learning, Non-photorealistic rendering, Silhouettes",
author = "Lum, {Eric B.} and Kwan-Liu Ma",
year = "2005",
month = "9",
day = "1",
doi = "10.1007/s00371-005-0342-y",
language = "English (US)",
volume = "21",
pages = "811--820",
journal = "Visual Computer",
issn = "0178-2789",
publisher = "Springer Verlag",
number = "8-10",

}

TY - JOUR

T1 - Expressive line selection by example

AU - Lum, Eric B.

AU - Ma, Kwan-Liu

PY - 2005/9/1

Y1 - 2005/9/1

N2 - An important problem in computer generated line drawing is determining which set of lines produces a representation that is in agreement with a user's communication goals. We describe a method that enables a user to intuitively specify which types of lines should appear in rendered images. Our method employs conventional silhouette-edge and other feature-line extraction algorithms to derive a set of candidate lines, and integrates machine learning into a user-directed line removal process using a sketching metaphor. The method features a simple and intuitive user interface that provides interactive control over the resulting line selection criteria and can be easily adapted to work in conjunction with existing line detection and rendering algorithms. Much of the method's power comes from its ability to learn the relationships between numerous geometric attributes that define a line style. Once learned, a user's style and intent can be passed from object to object as well as from view to view.

AB - An important problem in computer generated line drawing is determining which set of lines produces a representation that is in agreement with a user's communication goals. We describe a method that enables a user to intuitively specify which types of lines should appear in rendered images. Our method employs conventional silhouette-edge and other feature-line extraction algorithms to derive a set of candidate lines, and integrates machine learning into a user-directed line removal process using a sketching metaphor. The method features a simple and intuitive user interface that provides interactive control over the resulting line selection criteria and can be easily adapted to work in conjunction with existing line detection and rendering algorithms. Much of the method's power comes from its ability to learn the relationships between numerous geometric attributes that define a line style. Once learned, a user's style and intent can be passed from object to object as well as from view to view.

KW - Example-based rendering

KW - Machine learning

KW - Non-photorealistic rendering

KW - Silhouettes

UR - http://www.scopus.com/inward/record.url?scp=24944445450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24944445450&partnerID=8YFLogxK

U2 - 10.1007/s00371-005-0342-y

DO - 10.1007/s00371-005-0342-y

M3 - Article

AN - SCOPUS:24944445450

VL - 21

SP - 811

EP - 820

JO - Visual Computer

JF - Visual Computer

SN - 0178-2789

IS - 8-10

ER -