Extraction of hull features from images of indexed objects

Description

Hull features are a set of numeric descriptors of the hull of an object. These include coordinates, perimeter, size, acircularity etc.

Usage

  ## S4 method for signature 'IndexedImage':
  hullFeatures(x, ...)
  

Arguments

Details

The extracted features are (names carry an h. prefix to indicate hull features): x,y - coordinates of the geometric center, s - size (area), p - perimeter, pdm - mean distance to perimeter (from the center), pdsd - standard deviation of the distance to perimeter, effr - effective radius (is the radius of a circle with the same area), acirc - acircularity (fraction of pixels outside of the circle with r=reff), sf - shape factor (per / ( 2 * sqrt(Pi * s))), edge - number of pixels at the edge of the image, theta - hull's rotation angle (calculated without taking intensity values into account), s2maj - 2 times semi major (square root of the larger eigenvalue of the moments covariance matrix) - correlates with the distance from the center to the edge along the major axis, s2min - same but for the smaller eigenvalue (minor axis), ecc - eccentricity (sqrt(eig1-eig2)/smaj), I1, I2 - first and second rotation invariant moments of the hull (as in moments).

Value

For a single frame, a matrix of descriptors with objects in rows and features in columns. For image stacks, a list of such matrices.

Author(s)

Oleg Sklyar, osklyar@ebi.ac.uk, 2007

See Also

IndexedImage, watershed, getFeatures, edgeFeatures, moments

Examples

  ## see example(getFeatures)