deviation_n — Calculate standard deviation over several channels.
deviation_n(Image : ImageDeviation : : )
deviation_n generates the pixel-by-pixel standard deviation of
a multichannel gray value image. For each coordinate point p the expected
value is defined as the arithmetic mean:
where g_{c}(p) denominates the gray value at p on channel
c. n is the number of channels in the image.
The standard deviation itself is then calculated as: Note that this formula produces the sample standard deviation. The factor 2 is used to make better use of the range of values of the output image format. The output image has one channel.
Note that filter operators may return unexpected results if an image with a reduced domain is used as input. Please refer to the chapter Filters.
Image (input_object) (multichannel-)image(-array) → object (byte / int2 / uint2 / int4 / real)
Multichannel gray image.
ImageDeviation (output_object) image(-array) → object (byte / int2 / uint2 / int4 / real)
Result of calculation.
compose2,
compose3,
compose4,
compose5,
add_channels
Foundation