EdgeMagnitude

EdgeMagnitude[img, h] returns an edge image resulting from the application of edge operator h to image img.

EdgeMagnitude[img, {h₁, h₂, ...}] returns the magnitude of a gradient edge image resulting from the application of two or more directional edge operators to image img.

EdgeMagnitude[img, h] is effectively DiscreteConvolve[img, h, Centered→True].

GradientType → Automatic computes the gradient using the formula

where

_i is a directional derivative. Typically, n=2 and the derivatives are taken along the rows and columns of the image (PrewittFilter[], SobelFilter[]). In the case of the Frei-Chen edge operator, n=4.

GradientType → AbsValue uses the formula |

₁|+|

₂|+... .

The option GradientType → f defines a custom function f to compute the gradient magnitude. Function f must return a scalar and be a function of n arguments, where n is the number of edge masks. For example, to return the largest response from n masks, use GradientType→(Max[Abs[#1],Abs[#2],...,Abs[#n]]&).

GradientType → None returns a list of directional derivative images resulting from the application of each of the edge operators to the image img.

The option NonMaxSuppress→True permits the elimination (i.e., suppression) of edge responses that are not locally maximum. In effect this causes the thinning of the edges in the gradient image by suppressing gradient values with larger neighbors in the direction of the gradient.

The argument img may be a matrix or ImageData expression.