Semi‐Automatic Time‐Series Transfer Functions via Temporal Clustering and Sequencing
Open Access
- 1 June 2009
- journal article
- conference paper
- Published by Wiley in Computer Graphics Forum
- Vol. 28 (3) , 791-798
Abstract
When creating transfer functions for time‐varying data, it is not clear what range of values to use for classification, as data value ranges and distributions change over time. In order to generate time‐varying transfer functions, we search the data for classes that have similar behavior over time, assuming that data points that behave similarly belong to the same feature. We utilize a method we call temporal clustering and sequencing to find dynamic features in value space and create a corresponding transfer function. First, clustering finds groups of data points that have the same value space activity over time. Then, sequencing derives a progression of clusters over time, creating chains that follow value distribution changes. Finally, the cluster sequences are used to create transfer functions, as sequences describe the value range distributions over time in a data set.Keywords
This publication has 16 references indexed in Scilit:
- Visualization and exploration of time-varying medical image data setsProceedings. Graphics Interface (conference), 2007
- Intelligent Feature Extraction and Tracking for Visualizing Large-Scale 4D Flow Simulations2005
- Real time computation and temporal coherence of opacity transfer functions for direct volume rendering of ultrasound dataComputerized Medical Imaging and Graphics, 2005
- The State of the Art in Flow Visualisation: Feature Extraction and TrackingComputer Graphics Forum, 2003
- Semi-automatic generation of transfer functions for direct volume rendering2002
- Visualization of time-dependent data with feature tracking and event detectionThe Visual Computer, 2001
- A Study of Transfer Function Generation for Time-Varying Volume Data2001
- Semi-automatic generation of transfer functions for direct volume rendering1998
- Tracking and visualizing turbulent 3D featuresIEEE Transactions on Visualization and Computer Graphics, 1997
- Algorithm AS 136: A K-Means Clustering AlgorithmJournal of the Royal Statistical Society Series C: Applied Statistics, 1979