Parallel Coordinates Guided High Dimensional Transfer Function Design

TL;DR

This paper introduces a novel method combining parallel coordinate plots and dimensional reduction to improve high-dimensional transfer function design for volume rendering, enhancing data classification accuracy.

Contribution

It presents a new pipeline that integrates parallel coordinates with dimensional reduction to guide transfer function design in high-dimensional data visualization.

Findings

Effective visualization of CT and MRI datasets

Improved data classification for volume rendering

Enhanced transfer function design process

Abstract

High-dimensional transfer function design is widely used to provide appropriate data classification for direct volume rendering of various datasets. However, its design is a complicated task. Parallel coordinate plot (PCP), as a powerful visualization tool, can efficiently display high-dimensional geometry and accurately analyze multivariate data. In this paper, we propose to combine parallel coordinates with dimensional reduction methods to guide high-dimensional transfer function design. Our pipeline has two major advantages: (1) combine and display extracted high-dimensional features in parameter space; and (2) select appropriate high-dimensional parameters, with the help of dimensional reduction methods, to obtain sophisticated data classification as transfer function for volume rendering. In order to efficiently design high-dimensional transfer functions, the combination of both parallel coordinate components and dimension reduction results is necessary to generate final visualization results. We demonstrate the capability of our method for direct volume rendering using various CT and MRI datasets.