ISpace: interactive volume data classification techniques using independent component analysis

Author

Takanashi, Ikuko ; Lum, Eric B. ; Ma, Kwan-Liu ; Muraki, Shigeru

Author_Institution

Inf. Technol. R&D Center, Mitsubishi Electr. Corp., Japan

fYear

2002

fDate

2002

Firstpage

366

Lastpage

374

Abstract

This paper introduces an interactive classification technique for volume data, called ISpace, which uses Independent Component Analysis (ICA) and a multidimensional histogram of the volume data in a transformed space. Essentially, classification in the volume domain becomes equivalent to interactive clipping in the ICA space, which as demonstrated using several examples is more intuitive and direct for the user to classify data. The result is an opacity transfer function defined for rendering multivariate scalar volume data.

Keywords

data visualisation; image classification; independent component analysis; interactive systems; rendering (computer graphics); ISpace; independent component analysis; interactive classification; interactive clipping; interactive volume data classification techniques; multidimensional histogram; multivariate scalar volume data rendering; opacity transfer function; transformed space; volume data; volume domain; Biological materials; Biomedical imaging; Data visualization; Histograms; Image segmentation; Independent component analysis; Information technology; Rendering (computer graphics); Space technology; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Graphics and Applications, 2002. Proceedings. 10th Pacific Conference on

Print_ISBN

0-7695-1784-6

Type

conf

DOI

10.1109/PCCGA.2002.1167880

Filename

1167880