A Parallelized Surface Extraction Algorithm for Large Binary Image Data Sets Based on an Adaptive 3-D Delaunay Subdivision Strategy

  • Authors:
  • YingLiang Ma;Kurt Saetzler

  • Affiliations:
  • -;-

  • Venue:
  • IEEE Transactions on Visualization and Computer Graphics
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we describe a novel 3-D subdivision strategy to extract the surface of binary image data. This iterative approach generates a series of surface meshes that capture different levels of detail of the underlying structure. At the highest level of detail, the resulting surface mesh generated by our approach uses only about 10% of the triangles in comparison to the marching cube algorithm (MC) even in settings were almost no image noise is present. Our approach also eliminates the so-called 'staircase effect' which voxel based algorithms like the MC are likely to show, particularly if non-uniformly sampled images are processed. Finally, we show how the presented algorithm can be parallelized by subdividing 3-D image space into rectilinear blocks of subimages. As the algorithm scales very well with an increasing number of processors in a multi-threaded setting, this approach is suited to process large image data sets of several gigabytes. Although the presented work is still computationally more expensive than simple voxel based algorithms, it produces fewer surface triangles while capturing the same level of detail, is more robust towards image noise and eliminates the above mentioned 'stair-case' effect in anisotropic settings. These properties make it particularly useful for biomedical applications, where these conditions are often encountered.