hullFeatures {EBImage} | R Documentation |
Computes hull features from image objects.
hullFeatures(x)
x |
An Image object or an array containing object masks.
Object masks are sets of pixels with the same unique integer value. |
Extracted object features are:
g.x ,g.y
- coordinates of the geometric center.
g.s
- size in pixels.
g.p
- perimeter in pixels.
g.pdm
- mean distance from the center to perimeter.
g.pdsd
- standard deviation of the distance to perimeter.
g.effr
- effective radius (is the radius of a circle with the same area).
g.acirc
- acircularity (fraction of pixels outside of the circle with radius g.effr
).
g.sf
- shape factor, equals to (g.p/ ( 2*sqrt(i*g.s))
).
g.edge
- number of pixels at the edge of the image.
g.theta
- hull orientation angle, in radians. See above.
g.l1
- largest eigeinvalue of the covariance matrix. See above.
g.l2
- lowest eigenvalue of the covariance matrix. See above.
g.ecc
- eccentricity, equals to sqrt(1-g.l2/g.l1). See above.
g.I1, g.I2
- first and second Hu's translation/scale/rotation invariant moment. See above.
The features g.theta
, g.l1
, g.l2
, g.ecc
, g.I1
,
g.I2
are computed with the function moments
using the binary objects
as intensity values, e.g. g.theta = moment(x,x>0)[, 'm.theta']
. See moments
for details
on properties of these features.
A matrix (or a list of matrices if x
contains multiple frames) of
features computed of the objects present in x
.
Oleg Sklyar, osklyar@ebi.ac.uk, 2007
x = readImage(system.file('images', 'shapes.png', package='EBImage')) x = x[110:512,1:130] y = bwlabel(x) if (interactive()) display(normalize(y), title='Objects') ## hullFeatures hf = hullFeatures(y) print(hf)