ITK  4.1.0
Insight Segmentation and Registration Toolkit
MaskFeaturePointSelectionFilter Class Reference

#include <itkMaskFeaturePointSelectionFilter.h>


Detailed Description

Generate a PointSet containing the feature points selected from a masked 3D input image.

MaskFeaturePointSelectionFilter takes 3D image and 3D mask as inputs and generates a PointSet of feature points as output.

This filter is intended to be used for initializing the process of Physics-Based Non-Rigid Registration. It selects a fraction of non-masked points with highest variance. Optionally, tensors are computed for each point and stored as pixel values. [ M. Bierling, Displacement estimation by hierarchical block matching, Proc. SPIE Vis. Comm. and Image Proc., vol. 1001, pp. 942–951, 1988. ].

The filter is templated over input image and mask and output pointset.

Author:
Andriy Kot, Center for Real-Time Computing, Old Dominion University, Norfolk, VA
See also:
BlockMatchingImageFilter

The documentation for this class was generated from the following file: