[Insight-developers] new filter: SimilarityIndexImageFilter

[Lydia Ng]

FYI: I've checked in a new filter for computing similiarity between
the set of non-zero pixels of two images. This is useful=20
for validation when one needs to compare two segmentation masks.

See doc below for details.

- Lydia

/** \class SimilarityIndexImageFilter=20
 * \brief Measures the similarity between the set of non-zero pixels of=20
 * two images.
 *
 * SimilarityIndexImageFilter measures the similarity between the set
 * non-zero pixels of two images using the following formula:
 * \f[ S =3D \frac{2 | A \cap B |}{|A| + |B|} \f]
 * where \f$A\f$ and \f$B\f$ are respectively the set of non-zero pixels
 * in the first and second input images. Operator \f$|\cdot|\f$
represents
 * the size of a set and \f$\cap\f$ represents the intersection of two
sets.
 *
 * The measure is derived from a reliability measure known as the kappa
 * statistic. \f$S\f$ is sensitive to both differences in size and in
 * location and have been in the literature for comparing two
segmentation masks.=20
 * For more information see:
 * "Morphometric Analysis of White Matter Lesions in MR Images: Method
and
 * Validation", A. P. Zijdenbos, B. M. Dawant, R. A. Margolin and
 * A. C. Palmer, IEEE Trans. on Medical Imaging, 13(4) pp 716-724,1994
 *
 *
 * This filter requires all of its input images. It behaves as filter
with
 * two input and one output. Thus it can be inserted in a pipeline with=20
 * other filters. The filter passes the first input through unmodified.
 *
 * This filter is templated over the two input image type. It assume
 * both image have the same number of dimensions.
 *
 * \ingroup MultiThreaded
 */