Skip to contents

Labels objects

Source: R/utils_segmentation.R
object_label.Rd

All pixels for each connected set of foreground (non-zero) pixels in x are set to an unique increasing integer, starting from 1. Hence, max(x) gives the number of connected objects in x. This is a wrapper to EBImage::bwlabel or EBImage::watershed (if watershed = TRUE).

Usage

object_label(
  img,
  index = "B",
  invert = FALSE,
  fill_hull = FALSE,
  threshold = "Otsu",
  k = 0.1,
  windowsize = NULL,
  filter = FALSE,
  watershed = FALSE,
  tolerance = NULL,
  extension = NULL,
  object_size = "medium",
  plot = TRUE,
  ncol = NULL,
  nrow = NULL,
  verbose = TRUE
)

Arguments

img

An image object.

index

A character value (or a vector of characters) specifying the target mode for conversion to binary image. See the available indexes with pliman_indexes() and image_index() for more details.

invert

Inverts the binary image, if desired.

fill_hull

Fill holes in the objects? Defaults to FALSE.

threshold

The theshold method to be used.

  • By default (threshold = "Otsu"), a threshold value based on Otsu's method is used to reduce the grayscale image to a binary image. If a numeric value is informed, this value will be used as a threshold.

  • If threshold = "adaptive", adaptive thresholding (Shafait et al. 2008) is used, and will depend on the k and windowsize arguments.

  • If any non-numeric value different than "Otsu" and "adaptive" is used, an iterative section will allow you to choose the threshold based on a raster plot showing pixel intensity of the index.

k

a numeric in the range 0-1. when k is high, local threshold values tend to be lower. when k is low, local threshold value tend to be higher.

windowsize

windowsize controls the number of local neighborhood in adaptive thresholding. By default it is set to 1/3 * minxy, where minxy is the minimum dimension of the image (in pixels).

filter

Performs median filtering in the binary image? (Defaults to FALSE). Provide a positive integer > 1 to indicate the size of the median filtering. Higher values are more efficient to remove noise in the background but can dramatically impact the perimeter of objects, mainly for irregular perimeters such as leaves with serrated edges.

watershed

If TRUE (default) performs watershed-based object detection. This will detect objects even when they are touching one other. If FALSE, all pixels for each connected set of foreground pixels are set to a unique object. This is faster but is not able to segment touching objects.

tolerance

The minimum height of the object in the units of image intensity between its highest point (seed) and the point where it contacts another object (checked for every contact pixel). If the height is smaller than the tolerance, the object will be combined with one of its neighbors, which is the highest.

extension

Radius of the neighborhood in pixels for the detection of neighboring objects. Higher value smooths out small objects.

object_size

The size of the object. Used to automatically set up tolerance and extension parameters. One of the following. "small" (e.g, wheat grains), "medium" (e.g, soybean grains), "large"(e.g, peanut grains), and "elarge" (e.g, soybean pods)`.

plot

Show image after processing?

nrow, ncol

The number of rows or columns in the plot grid. Defaults to NULL, i.e., a square grid is produced.

verbose

If TRUE (default) a summary is shown in the console.

Value

A list with the same length of img containing the labeled objects.

Examples

img <- image_pliman("soybean_touch.jpg")
# segment the objects using the "B" (blue) band.
object_label(img, index = "B")

object_label(img, index = "B", watershed = TRUE)