Binary segmentation

Description

Labels connected (connected sets) objects in a binary image.

Usage

  bwlabel(x)

Arguments

Details

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.

Value

An Grayscale Image object or an array, containing the labelled version of x.

Author(s)

Gregoire Pau, 2009

Examples

  ## simple example
  x = readImage(system.file('images', 'shapes.png', package='EBImage'))
  x = x[110:512,1:130]
  if (interactive()) display(x, title='Binary')
  y = bwlabel(x)
  if (interactive()) display(normalize(y), title='Segmented')

  ## read nuclei images
  x = readImage(system.file('images', 'nuclei.tif', package='EBImage'))
  if (interactive()) display(x)

  ## computes binary mask
  y = thresh(x, 10, 10, 0.05)
  y = opening(y, makeBrush(5, shape='disc'))
  if (interactive()) display(y, title='Cell nuclei binary mask')

  ## bwlabel
  z = bwlabel(y)
  if (interactive()) display(normalize(z), title='Cell nuclei')
  nbnuclei = apply(z, 3, max)
  cat('Number of nuclei=', paste(nbnuclei, collapse=','),'\n')

  ## recolor nuclei in colors
  cols = c('black', sample(rainbow(max(z))))
  zrainbow = Image(cols[1+z], dim=dim(z))
  if (interactive()) display(zrainbow, title='Cell nuclei (recolored)')