Harmonic Cut and Regularized Centroid Transform for Localization of Subceullar Structures
IEEE Transaction on Biomedical Engineering, April 2003.
Two novel computational techniques, harmonic cut and
regularized centroid transform ,
are developed for segmentation of cells and their
corresponding substructures observed with an
Harmonic cut detects small regions that correspond to
small subcellular structures. These regions also affect
the accuracy of the overall segmentation.
They are detected, removed, and interpolated to ensure continuity within
each region. We show that interpolation within each region (subcellular
compartment) is equivalent to
solving the Laplace equation on
a multi-connected domain with irregular boundaries.
The second technique, referred to as the regularized centroid transform,
aims to separate touching compartments.
This is achieved by adopting a quadratic model for the shape of
the object and relaxing it for final segmentation.
click here to see the
full version of journal paper in PDF format