Image filter and manipulation (`medpy.filter`)#

This package contains various image filters and image manipulation functions.

Smoothing `medpy.filter.smoothing`#

Image smoothing / noise reduction in grayscale images.

`anisotropic_diffusion`(img[, niter, kappa, ...])	Edge-preserving, XD Anisotropic diffusion.
`gauss_xminus1d`(img, sigma[, dim])	Applies a X-1D gauss to a copy of a XD image, slicing it along dim.

Binary image manipulation.

`size_threshold`(img, thr[, comp, structure])	Removes binary objects from an image identified by a size threshold.
`largest_connected_component`(img[, structure])	Select the largest connected binary component in an image.
`bounding_box`(img)	Return the bounding box incorporating all non-zero values in the image.

Grayscale image manipulation.

`sls`(minuend, subtrahend[, metric, noise, ...])	Computes the signed local similarity between two images.
`ssd`(minuend, subtrahend[, normalized, ...])	Computes the sum of squared difference (SSD) between patches of minuend and subtrahend.
`average_filter`(input[, size, footprint, ...])	Calculates a multi-dimensional average filter.
`sum_filter`(input[, size, footprint, output, ...])	Calculates a multi-dimensional sum filter.
`local_minima`(img[, min_distance])	Returns all local minima from an image.
`otsu`(img[, bins])	Otsu's method to find the optimal threshold separating an image into fore- and background.
`resample`(img, hdr, target_spacing[, ...])	Re-sample an image to a new voxel-spacing.

Global and local noise estimation in grayscale images.

`immerkaer`(input[, mode, cval])	Estimate the global noise.
`immerkaer_local`(input, size[, output, mode, ...])	Estimate the local noise.
`separable_convolution`(input, weights[, ...])	Calculate a n-dimensional convolution of a separable kernel to a n-dimensional input.

Utilities to apply filters selectively and create your own ones.

`xminus1d`(img, fun, dim, args, *kwargs)	Applies the function fun along all X-1D dimensional volumes of the images img dimension dim.
`intersection`(i1, h1, i2, h2)	Returns the intersecting parts of two images in real world coordinates.
`pad`(input[, size, footprint, output, mode, cval])	Returns a copy of the input, padded by the supplied structuring element.

The hough transform shape detection algorithm.

`ght`(img, template)	Implementation of the general hough transform for all dimensions.
`ght_alternative`(img, template, indices)	Alternative implementation of the general hough transform, which uses iteration over indices rather than broadcasting rules like `ght`.
`template_ellipsoid`(shape)	Returns an ellipsoid binary structure of a of the supplied radius that can be used as template input to the generalized hough transform.
`template_sphere`(radius, dimensions)	Returns a spherical binary structure of a of the supplied radius that can be used as template input to the generalized hough transform.

A learning method to align the intensity ranges of images.

Class to standardize intensity ranges between a number of images.

`relabel_map`(label_image, mapping[, key])	Relabel an image using the supplied mapping.
`relabel`(label_image[, start])	Relabel the regions of a label image.
`relabel_non_zero`(label_image[, start])	Relabel the regions of a label image.
`fit_labels_to_mask`(label_image, mask)	Reduces a label images by overlaying it with a binary mask and assign the labels either to the mask or to the background.