Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Techniques for precision-based visual analysis of projected data

: Schreck, Tobias; Landesberger, Tatiana von; Bremm, Sebastian


Park, J. ; Society for Imaging Science and Technology -IS&T-; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Visualization and Data Analysis 2010 : 18 January 2010, San Jose, California, USA
Bellingham, WA: SPIE, 2010 (Proceedings of SPIE 7530)
ISBN: 978-0-8194-7923-5
Paper 7500E
Conference on Visualization and Data Analysis (VDA) <2010, San Jose/Calif.>
Conference Paper
Fraunhofer IGD ()
multidimensional data visualization; data reduction; quality evaluation; point cloud; Forschungsgruppe Visual Search and Analysis (VISA)

The analysis of high-dimensional data is an important, yet inherently difficult problem. Projection techniques such as PCA, MDS, and SOM can be used to map high-dimensional data to 2D display space. However, projections typically incur a loss in information. Often uncertainty exists regarding the precision of the projection as compared with its original data characteristics. While the output quality of these projection techniques can be discussed in terms of algorithmic assessment, visualization is often helpful for better understanding the results.
We address the visual assessment of projection precision by an approach integrating an appropriately designed projection precision measure directly into the projection visualization. To this end, a flexible projection precision measure is defined that allows the user to balance the degree of locality at which the measure is evaluated. Several visual mappings are designed for integrating the precision measure into the projection visualization at various levels of abstraction. The techniques are implemented in a fully interactive system which is practically applied on several data sets. We demonstrate the usefulness of the approach for visual analysis of classified and clustered high-dimensional data sets. We thereby show how our novel interactive precision quality visualization system helps to examine preservation of closeness of the data in original space into the low-dimensional space.