zca whiten of an image

Share:

Description

this function performs zca-whitening to a 2- or 3- dimensional image

Usage

1
ZCAwhiten(image, k, epsilon)

Arguments

image

a matrix, data frame or 3-dimensional array

k

an integer specifying the number of components to keep when svd is performed (reduced dimension representation of the data)

epsilon

a float specifying the regularization parameter

Details

Whitening (or sphering) is the preprocessing needed for some algorithms. If we are training on images, the raw input is redundant, since adjacent pixel values are highly correlated. When using whitening the features become less correlated and all features have the same variance.

Value

a matrix or 3-dimensional array

References

http://ufldl.stanford.edu/wiki/index.php/Whitening

Examples

1
2
3
4
5
path = system.file("tmp_images", "1.png", package = "OpenImageR")

image = readImage(path)

res = ZCAwhiten(image, k = 20, epsilon = 0.1)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.