Finding Textures in Sketches using Planar Ising Models

Matthew D. McLure, S. Kandaswamy, Kenneth D Forbus

Research output: Contribution to conferencePaper

Abstract

Creating software that can understand the range of sketches that people produce is a challenging problem. One source of difficulty is that people often include textures in their drawings. This paper shows how to use Ising models, a technique from computer vision at the level of pixels, for decomposing digital ink into a hierarchy of edge-based structures that provide more concise qualitative representations of textures in hand-drawn sketches. We analyze the compression efficacy, strengths and weaknesses of this qualitative representation technique using a subset of a large-scale sketch corpus.
Original languageEnglish (US)
Number of pages9
StatePublished - 2015

Fingerprint

Ising model
Textures
Ink
Computer vision
Pixels

Cite this

@conference{7d9b00657ef04f369fc9745d75b6e252,
title = "Finding Textures in Sketches using Planar Ising Models",
abstract = "Creating software that can understand the range of sketches that people produce is a challenging problem. One source of difficulty is that people often include textures in their drawings. This paper shows how to use Ising models, a technique from computer vision at the level of pixels, for decomposing digital ink into a hierarchy of edge-based structures that provide more concise qualitative representations of textures in hand-drawn sketches. We analyze the compression efficacy, strengths and weaknesses of this qualitative representation technique using a subset of a large-scale sketch corpus.",
author = "McLure, {Matthew D.} and S. Kandaswamy and Forbus, {Kenneth D}",
year = "2015",
language = "English (US)",

}

Finding Textures in Sketches using Planar Ising Models. / McLure, Matthew D.; Kandaswamy, S.; Forbus, Kenneth D.

2015.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Finding Textures in Sketches using Planar Ising Models

AU - McLure, Matthew D.

AU - Kandaswamy, S.

AU - Forbus, Kenneth D

PY - 2015

Y1 - 2015

N2 - Creating software that can understand the range of sketches that people produce is a challenging problem. One source of difficulty is that people often include textures in their drawings. This paper shows how to use Ising models, a technique from computer vision at the level of pixels, for decomposing digital ink into a hierarchy of edge-based structures that provide more concise qualitative representations of textures in hand-drawn sketches. We analyze the compression efficacy, strengths and weaknesses of this qualitative representation technique using a subset of a large-scale sketch corpus.

AB - Creating software that can understand the range of sketches that people produce is a challenging problem. One source of difficulty is that people often include textures in their drawings. This paper shows how to use Ising models, a technique from computer vision at the level of pixels, for decomposing digital ink into a hierarchy of edge-based structures that provide more concise qualitative representations of textures in hand-drawn sketches. We analyze the compression efficacy, strengths and weaknesses of this qualitative representation technique using a subset of a large-scale sketch corpus.

M3 - Paper

ER -