Plugin type: 2dimage/cost

2D image similarity kernels evaluate the according similarity measure between two images. These kernels may be used standalone, like e.g. in linear registration, or will be called from generalized image similarity cost plug-ins that also take care of transforming and scaling the images during the image registration process.

Plugins:

lsd mi ngf ssd

lsd

Least-Squares Distance measure. (This plug-in doesn't take parameters)

mi

Spline parzen based mutual information.. Supported parameters are:

NameTypeDefaultDescription
cutfloat0Percentage of pixels to cut at high and low intensities to remove outliers in [0, 40]
mbinsuint64Number of histogram bins used for the moving image in [1, 256]
mkernelfactory[bspline:d=3]Spline kernel for moving image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel
rbinsuint64Number of histogram bins used for the reference image in [1, 256]
rkernelfactory[bspline:d=0]Spline kernel for reference image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel

ngf

This function evaluates the image similarity based on normalized gradient fields. Various evaluation kernels are availabe.. Supported parameters are:

NameTypeDefaultDescription
evalstringdsplugin subtype (sq, ds,dot,cross)

ssd

2D imaga cost: sum of squared differences. Supported parameters are:

NameTypeDefaultDescription
normbool0Set whether the metric should be normalized by the number of image pixels

Plugin consumers:

mia-2dcost mia-2dimageregistration mia-2dmany2one-nonrigid mia-2dmyoica-nonrigid mia-2dmyoica-nonrigid-parallel mia-2dmyoperiodic-nonrigid mia-2dmyoserial-nonrigid mia-2dmyoset-all2one-nonrigid image:2dimage/fullcost