3D 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.
Spline parzen based mutual information.. Supported parameters are:
Name | Type | Default | Description |
---|---|---|---|
cut | float | 0 | Percentage of pixels to cut at high and low intensities to remove outliers in [0, 40] |
mbins | uint | 64 | Number of histogram bins used for the moving image in [1, 256] |
mkernel | factory | [bspline:d=3] | Spline kernel for moving image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel |
rbins | uint | 64 | Number of histogram bins used for the reference image in [1, 256] |
rkernel | factory | [bspline:d=0] | Spline kernel for reference image parzen hinstogram. For supported plug-ins see Plugin type: 1d/splinekernel |
This function evaluates the image similarity based on normalized gradient fields. Given normalized gradient fields $ _S$ of the src image and $ _R$ of the ref image various evaluators are implemented.. Supported parameters are:
Name | Type | Default | Description |
---|---|---|---|
eval | string | ds | plugin subtype (sq, ds,dot,cross) |
3D image cost: sum of squared differences. Supported parameters are:
Name | Type | Default | Description |
---|---|---|---|
norm | bool | 0 | Set whether the metric should be normalized by the number of image pixels |