GLCM feature texture extraction

GLCM feature texture extraction

GLCM feature texture extraction

Usage

# init <- fastglcm$new()

Methods

fastglcm$new()

--------------

GLCM_compute()

--------------

References

https://github.com/tzm030329/GLCM https://github.com/1044197988/Python-Image-feature-extraction

Methods

Public methods

• fastglcm$new()

• fastglcm$GLCM_compute()

• fastglcm$clone()

---

Method new()

Initialization method for the 'fastglcm' R6 class

Usage

fastglcm$new()

---

Method GLCM_compute()

The GLCM computation method to receive the results

Usage

fastglcm$GLCM_compute(
  img,
  method,
  vmin = 0,
  vmax = 255,
  levels = 8,
  ks = 5,
  distance = 1,
  angle = 0,
  verbose = FALSE
)

Arguments

img

a numeric matrix

method

a character string specifying the method. Can be one of 'mean', 'std', 'contrast', 'dissimilarity', 'homogeneity', 'ASM_Energy', 'max' or 'entropy'

vmin

a numeric value specifying the minimum value of the input image ( img )

vmax

a numeric value specifying the maximum value of the input image ( img )

levels

an integer specifying the window size. This parameter will create a mask of size levels x levels internally

ks

an integer specifying the kernel size. A kernel of 1's will be created and the cv2.filter2D filter will be utilized for the convolution

distance

a numeric value specifying the pixel pair distance offsets (a 'pixel' value such as 1.0, 2.0 etc.)

angle

a numeric value specifying the pixel pair angles (a 'degree' value such as 0.0, 30.0, 45.0, 90.0 etc.)

verbose

a boolean. If TRUE then information will be printed out in the console

Returns

a list object if the method is set to 'ASM_Energy' otherwise a numeric matrix

---

Method clone()

The objects of this class are cloneable with this method.

Usage

fastglcm$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

if (FALSE) { # \dontrun{

require(fastGLCM)
require(OpenImageR)

file_im = system.file('images', 'Sugar_Cane_Bolivia_PlanetNICFI.png', package = 'fastGLCM')
im = readImage(file_im)

#...................................
# convert to gray and make sure that
# pixel values are between 0 and 255
#...................................

im = rgb_2gray(im)
im = im * 255

MIN = min(as.vector(im))
MAX = max(as.vector(im))

#...............
# methods to use
#...............

methods_py = c('mean',
               'std',
               'contrast',
               'dissimilarity',
               'homogeneity',
               'ASM_Energy',
               'max',
               'entropy')

init = fastglcm$new()

lst_glcm_py = list()

for (item_m in methods_py) {

  cat(paste0('Method: ', item_m), '\n')

  res_item = init$GLCM_compute(img = im,
                               method = item_m,
                               vmin = as.integer(MIN),
                               vmax = as.integer(MAX),
                               levels = as.integer(8),
                               ks = as.integer(5),
                               distance = 1.0,
                               angle = 0.0)

  lst_glcm_py[[item_m]] = res_item
}

#..............................
# Create two different sublists
# for 'ASM' and 'Energy'
#..............................

lst_glcm_py = append(lst_glcm_py, list(lst_glcm_py[['ASM_Energy']][[1]]), after = 5)
names(lst_glcm_py)[6] = 'ASM'

lst_glcm_py = append(lst_glcm_py, list(lst_glcm_py[['ASM_Energy']][[2]]), after = 6)
names(lst_glcm_py)[7] = 'energy'

lst_glcm_py[['ASM_Energy']] = NULL

str(lst_glcm_py)

#.........................
# multi-plot of the output
#.........................

plot_multi_images(list_images = lst_glcm_py,
                  par_ROWS = 2,
                  par_COLS = 5,
                  titles = names(lst_glcm_py))
} # }