3D image similarity kernels evaluate the according similarity measure between two images by using a mask. 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.
local normalized cross correlation with masking support.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| w | uint in [1, 256] | 5 | half width of the window used for evaluating the localized cross correlation |
Spline parzen based mutual information with masking.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| cut | float in [0, 40] | 0 | Percentage of pixels to cut at high and low intensities to remove outliers |
| mbins | uint in [1, 256] | 64 | Number of histogram bins used for the moving image |
| mkernel | factory | [bspline:d=3] | Spline kernel for moving image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel |
| rbins | uint in [1, 256] | 64 | Number of histogram bins used for the reference image |
| rkernel | factory | [bspline:d=0] | Spline kernel for reference image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel |
mia-3dcost mia-3dmany2one-nonrigid mia-3dnonrigidreg mia-3dnonrigidreg-alt mia-3dprealign-nonrigid mia-3dserial-nonrigid maskedimage:3dimage/fullcost