Interactive volume classification and visualisation using incremenal-svm and cuda

Authors: David M. Hughes, Ik Soo Lim, Nigel John, Keith Hughes and Tom Rippeth

ISBN: 978-972-8939-22-9

Abstract:

This paper presents a work-in-progress interactive tool for the visualization of volumetric data using higher-dimensional classification. The conversion of volume cells to multi-dimensional training examples enables classification results not achievable by standard DVR transfer-function methods. A user specifies input for a Support Vector Machine (SVM) which is trained to predict the classification of each remaining voxel in a volume. By utilizing Incremental SVM, our segmentation tool is able to hide the training process during the user painting period such that any delay between the moment the user stops painting to the final visualization is minimized. In order to accelerate the class prediction of the entire volume we employ CUDA-enabled GPUs, which results in more than a ten-fold decrease in the time needed when
compared to CPU-based methods.

Link to Paper

Authors

Prof. Nigel John

Prof John's primary research interests are in the application of computer graphics, haptics and virtual environments to medical applications.

Dr Ik Soo Lim

Digital Geometry Processing, Volumetric Data Visualization, Hyperspectral Image Visualisation Visual Perception, Computational Psychology, Computational Biology.