A normalization kernel applied across feature channels.


The normalization kernel applies the kernel to a local region across nearby feature channels, but with no spatial extent (i.e., they have the shape kernel size x 1 x 1). The normalized output is given by the function:

Y(i,j,k) = X(i,j,k) / L(i,j,k)^beta

Where the normalizing factor is:

L(i,j,k) = delta + alpha/N * (sum_{q in Q(k)} X(i,j,q)^2

Where N is the kernel size. The window Q(k) itself is defined as:

Q(k) = [max(0, k-floor(N/2)), min(D-1, k+floor((N-1)/2)]

Where k is the feature channel index (running from 0 to D-1) and D is the number of feature channels, and the values of alpha, beta, and delta are set via properties.

It is your responsibility to ensure that the combination of the values of the delta and alpha properties does not result in a situation where the denominator becomes zero - in such situations the resulting pixel-value is undefined.


Instance Properties


The "alpha" variable of the kernel function.


The "beta" variable of the kernel function.


The "delta" variable of the kernel function.


The size of the square kernel window.


Inherits From

See Also

Normalization Layers


A local contrast normalization kernel.


A spatial normalization kernel.

Beta Software

This documentation contains preliminary information about an API or technology in development. This information is subject to change, and software implemented according to this documentation should be tested with final operating system software.

Learn more about using Apple's beta software