SLIC and SLICO superpixel implementations

superpixels(
  input_image,
  method = "slic",
  superpixel = 200,
  compactness = 20,
  return_slic_data = FALSE,
  return_lab_data = FALSE,
  return_labels = FALSE,
  write_slic = "",
  verbose = FALSE
)

Arguments

input_image: either a 2-dimensional or a 3-dimensional input image where the third dimension is equal to 3 (the range of the pixel values should be preferably in the range 0 to 255)
method: a character string specifying the method to use. Either "slic" or "slico"
superpixel: a numeric value specifying the number of superpixels to use
compactness: a numeric value specifying the compactness parameter. The compactness parameter is needed only if method is "slic". The "slico" method adaptively chooses the compactness parameter for each superpixel differently.
return_slic_data: a boolean. If TRUE then the resulted slic or slico data will be returned
return_lab_data: a boolean. If TRUE then the Lab data will be returned ( the Lab-colour format )
return_labels: a boolean. If TRUE then the labels will be returned
write_slic: a character string. If not an empty string ("") then it should be a path to the output file with extension .bin ( for instance "/my_dir/output.bin" ). The data will be saved in binary format.
verbose: a boolean. If TRUE then information will be printed in the R session

References

https://www.epfl.ch/labs/ivrl/research/slic-superpixels/

Examples


library(OpenImageR)

#-------------------
# 3-dimensional data
#-------------------

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

im = readImage(path)

res = superpixels(input_image = im, method = "slic", superpixel = 200,

                  compactness = 20, return_slic_data = TRUE)
#> Warning: The input data has more than 3 dimensions. The dimensions were reduced from 4 to 3!
#> Warning: The input data has values between 0.094118 and 1.000000. The image-data will be multiplied by the value: 255!


#-------------------
# 2-dimensional data
#-------------------

im_2d = im[,,1]

res_mt = superpixels(input_image = im_2d, method = "slic", superpixel = 200,

                     compactness = 20, return_slic_data = TRUE)
#> Warning: The input data has values between 0.149020 and 1.000000. The image-data will be multiplied by the value: 255!