ll_boundaries Extract meaningful boundaries (contrasted level lines) from a Fimage
ll_boundaries [-e eps] [-a] [-w] [-s step] [-p p] [-t tree] [-z] in out
-e eps : -log10(max. number of false alarms), default 0
-a : get all contrasted level lines (not only maximal ones)
-w : select weak maximality
-s step : quantization step (bilinear), default 1.
-p p : sampling precision (bilinear), default 2
-t tree : use a precomputed FLST tree
-z : use zero order instead of bilinear interpolation
in : input Fimage
out : output boundaries (Flists)
Flists ll_boundaries (in , tree , eps , all , step , precision , z , weak )
Fimage in ;
Shapes tree ;
float *eps , *step ;
int *precision ;
char *all , *z , *weak ;
This modules computes all the level lines (that is, the connected
components of the boundaries of the level sets) of an image
(with the same options
ll_extract module) and keeps the most contrasted ones.
The detection is made using a thresholding function balancing between
the minimum contrast (gradient norm) along the curve and the
length of the curve. Unless
-a option is specified, only
on representant (the most meaningful one) is kept for each
monotone sequence of meaningful level lines (that is, a sequence
of level lines included in each others, with no inclusion
branching and no contrast reversal).
The thresholding function ensures
that at most 10-eps false detections could occur by chance
with independent random gradient values (see [DMM01]).
Notice that contrary to the
ll_edges detection, this
module is constrained to keep full (ie closed) level lines and
cannot break them into parts.
The result is a collection of curves stored in a Flists structure.
fderiv, fhisto, flst, flstb_boundary, flst_bilinear, flst_boundary, flstb_quantize, fsaddles, sintegral.
Last Modification date : Tue Apr 8 16:46:18 2003