Learn R Programming

mmand (version 1.6.3)

gaussianSmooth: Smooth a numeric array with a Gaussian kernel

Description

This function smoothes an array using a Gaussian kernel with a specified standard deviation.

Usage

gaussianSmooth(x, sigma)

Value

A morphed array with the same dimensions as the original array.

Arguments

x

An object that can be coerced to an array, or for which a morph method exists.

sigma

A numeric vector giving the standard deviation of the kernel in each dimension. Can have lower dimensionality than the target array.

Author

Jon Clayden <code@clayden.org>

Details

This implementation takes advantage of the separability of the Gaussian kernel for speed when working in multiple dimensions. It is therefore equivalent to, but much faster than, directly applying a multidimensional kernel.

See Also

morph for the function underlying this operation, gaussianKernel for generating Gaussian kernels (which is also used by this function), and erode for mathematical morphology functions.