Image.segment

Segments an image by analyzing the histograms of the color components and identifying units that are homogeneous with the fuzzy c-means technique. Also uses quantizeColorSpace and verbose image properties.

class Image
void
segment
(
double clusterThreshold = 1
,
double smoothingThreshold = 1.5
)

Parameters

clusterThreshold
Type: double

The number of pixels in each cluster must exceed the the cluster threshold to be considered valid.

smoothingThreshold
Type: double

The smoothing threshold eliminates noise in the second derivative of the histogram. As the value is increased, you can expect a smoother second derivative.

Meta