Learning Probabilistic Transfer Functions: A Comparative Study of Classifiers. (June 2015)

• Record Type: Journal Article
• Authors: Soundararajan, K. P.; Schultz, T.
• Is Part Of: Computer graphics forum. Volume 34:Number 3(2015)
• Page Start: 111
• Page End: 120
• Publication Date: 2015-06
• Subjects: Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.12623
• Languages: English
• ISSNs: 0167-7055

Abstract

<abstract abstract-type="main"> <title>Abstract</title> <p>Complex volume rendering tasks require high‐dimensional transfer functions, which are notoriously difficult to design. One solution to this is to learn transfer functions from scribbles that the user places in the volumetric domain in an intuitive and natural manner. In this paper, we explicitly model and visualize the uncertainty in the resulting classification. To this end, we extend a previous intelligent system approach to volume rendering, and we systematically compare five supervised classification techniques – Gaussian Naive Bayes, k Nearest Neighbor, Support Vector Machines, Neural Networks, and Random Forests – with respect to probabilistic classification, support for multiple materials, interactive performance, robustness to unreliable input, and easy parameter tuning, which we identify as key requirements for the successful use in this application. Based on theoretical considerations, as well as quantitative and visual results on volume datasets from different sources and modalities, we conclude that, while no single classifier can be expected to outperform all others under all circumstances, random forests are a useful off‐the‐shelf technique that provides fast, easy, robust and accurate results in many scenarios.</p> </abstract>