High-Resolution Reconstruction of Sparse Data from Dense Low-Resolution Spatio-Temporal Data
International Conference on Pattern Recognition, Aug. 2002..
We present an efficient protocol for robust detection of
3D blobs from volumetric datasets.
The approach has three steps. The first step of the
process detects elliptic features by classifying the Hessian of the
scale space representation of the volume data.
These features are then grouped into 3D
connected components, which are subsequently
partitioned by computing a convex hull of each connected component.
The proposed framework has been applied to a database of
multicellular systems for detailed quantitative analysis.
click here to see the
full version of journal paper in PostScript format