An intelligent system approach to higher-dimensional classification of volume data

Fan Yin Tzeng, Eric B. Lum, Kwan-Liu Ma

Research output: Contribution to journalArticle

110 Citations (Scopus)

Abstract

In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties In working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an Intuitive manner. The user works In the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.

Original languageEnglish (US)
Pages (from-to)273-283
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Volume11
Issue number3
DOIs
StatePublished - May 1 2005

Fingerprint

Intelligent systems
Painting
Transfer functions
Data visualization
Opacity
Visibility
Learning systems
Color
Feedback
Hardware

Keywords

  • Classification
  • Graphics hardware
  • Machine learning
  • Transfer functions
  • User interface design
  • Visualization
  • Volume rendering

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

An intelligent system approach to higher-dimensional classification of volume data. / Tzeng, Fan Yin; Lum, Eric B.; Ma, Kwan-Liu.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 11, No. 3, 01.05.2005, p. 273-283.

Research output: Contribution to journalArticle

@article{52867a0a0abe46099cb8bb6fd2836b7a,
title = "An intelligent system approach to higher-dimensional classification of volume data",
abstract = "In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties In working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an Intuitive manner. The user works In the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.",
keywords = "Classification, Graphics hardware, Machine learning, Transfer functions, User interface design, Visualization, Volume rendering",
author = "Tzeng, {Fan Yin} and Lum, {Eric B.} and Kwan-Liu Ma",
year = "2005",
month = "5",
day = "1",
doi = "10.1109/TVCG.2005.38",
language = "English (US)",
volume = "11",
pages = "273--283",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - An intelligent system approach to higher-dimensional classification of volume data

AU - Tzeng, Fan Yin

AU - Lum, Eric B.

AU - Ma, Kwan-Liu

PY - 2005/5/1

Y1 - 2005/5/1

N2 - In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties In working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an Intuitive manner. The user works In the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.

AB - In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties In working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an Intuitive manner. The user works In the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.

KW - Classification

KW - Graphics hardware

KW - Machine learning

KW - Transfer functions

KW - User interface design

KW - Visualization

KW - Volume rendering

UR - http://www.scopus.com/inward/record.url?scp=17444421585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17444421585&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2005.38

DO - 10.1109/TVCG.2005.38

M3 - Article

C2 - 15868827

AN - SCOPUS:17444421585

VL - 11

SP - 273

EP - 283

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 3

ER -