calculate the HOG (Histogram of oriented gradients) for an image

The function is a modification of the 'findHOGFeatures' function of the SimpleCV package [ please consult the COPYRIGHT file ] The function takes either an RGB (it will be converted to gray) or a gray image and returns a vector of the HOG descriptors. The main purpose of the function is to create a vector of features, which can be used in classification tasks.

HOG(image, cells = 3, orientations = 6)

Arguments

image: matrix or 3-dimensional array where the third dimension is equal to 3
cells: the number of divisions ( cells )
orientations: number of orientation bins

Value

a numeric vector

Details

This function takes either a matrix, a data frame or a 3-dimensional array (where the third dimension is equal to 3) and returns a vector with the HOG-descriptors (histogram of oriented gradients).

Examples


if (FALSE) {

path = system.file("tmp_images", "1.png", package = "OpenImageR")

image = readImage(path)

res = HOG(image, cells = 3, orientations = 6)
}