Name
points_lepetitT_points_lepetitPointsLepetitpoints_lepetitPointsLepetitPointsLepetit — Detect points of interest using the Lepetit operator.
Herror points_lepetit(Hobject Image, const HTuple& Radius, const HTuple& CheckNeighbor, const HTuple& MinCheckNeighborDiff, const HTuple& MinScore, const HTuple& Subpix, HTuple* Row, HTuple* Column)
HTuple HImage::PointsLepetit(const HTuple& Radius, const HTuple& CheckNeighbor, const HTuple& MinCheckNeighborDiff, const HTuple& MinScore, const HTuple& Subpix, HTuple* Column) const
void PointsLepetit(const HObject& Image, const HTuple& Radius, const HTuple& CheckNeighbor, const HTuple& MinCheckNeighborDiff, const HTuple& MinScore, const HTuple& Subpix, HTuple* Row, HTuple* Column)
void HImage::PointsLepetit(Hlong Radius, Hlong CheckNeighbor, Hlong MinCheckNeighborDiff, Hlong MinScore, const HString& Subpix, HTuple* Row, HTuple* Column) const
void HImage::PointsLepetit(Hlong Radius, Hlong CheckNeighbor, Hlong MinCheckNeighborDiff, Hlong MinScore, const char* Subpix, HTuple* Row, HTuple* Column) const
void HOperatorSetX.PointsLepetit(
[in] IHUntypedObjectX* Image, [in] VARIANT Radius, [in] VARIANT CheckNeighbor, [in] VARIANT MinCheckNeighborDiff, [in] VARIANT MinScore, [in] VARIANT Subpix, [out] VARIANT* Row, [out] VARIANT* Column)
VARIANT HImageX.PointsLepetit(
[in] Hlong Radius, [in] Hlong CheckNeighbor, [in] Hlong MinCheckNeighborDiff, [in] Hlong MinScore, [in] BSTR Subpix, [out] VARIANT* Column)
static void HOperatorSet.PointsLepetit(HObject image, HTuple radius, HTuple checkNeighbor, HTuple minCheckNeighborDiff, HTuple minScore, HTuple subpix, out HTuple row, out HTuple column)
void HImage.PointsLepetit(int radius, int checkNeighbor, int minCheckNeighborDiff, int minScore, string subpix, out HTuple row, out HTuple column)
points_lepetitpoints_lepetitPointsLepetitpoints_lepetitPointsLepetitPointsLepetit extracts points of interest like corners or
blob-like structures from ImageImageImageImageImageimage. The ImageImageImageImageImageimage is first
smoothed with a median of size 3x3. Then, all the gray values on a circle
with radius RadiusRadiusRadiusRadiusRadiusradius around an interest point candidate
(m) are examined. The absolute differences of two diagonally
opposed gray values (m1,m2) on the circle to the central pixel
m is computed. At least one of these differences has to be
larger than MinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffminCheckNeighborDiff. All diagonally opposed pixels
on the circle must fulfill that condition. To suppress detection of
points at edges that have a small curvature (aliasing), it is possible
to compute CheckNeighborCheckNeighborCheckNeighborCheckNeighborCheckNeighborcheckNeighbor further differences of circle point
neighbors of m1 and m2 to the center, that as well
fulfill the above criteria. By computing all gray value differences of
the circle points to the center, a mean gray value difference is
determined. That value has to be larger than MinScoreMinScoreMinScoreMinScoreMinScoreminScore and
allows to restrict the results to points with high contrast. By computing
the score of all eight neighbors of m, it is possible to fit a quadratic
equation to that. The maxima of that equation determines a subpixel
accurate interest point position. By setting the parameter SubpixSubpixSubpixSubpixSubpixsubpix
to 'interpolation' (default) or 'none', it is possible to turn that refinement
step on or off. The resulting points are returned in RowRowRowRowRowrow and
ColumnColumnColumnColumnColumncolumn. The operator points_lepetitpoints_lepetitPointsLepetitpoints_lepetitPointsLepetitPointsLepetit can especially be
used for very fast interest point extraction. The results are however
less robust than points extracted by points_harrispoints_harrisPointsHarrispoints_harrisPointsHarrisPointsHarris for example.
Note that filter operators may return unexpected results if
an image with a reduced domain is used as input. Please refer to the
chapter Filters.
- Multithreading type: reentrant (runs in parallel with non-exclusive operators).
- Multithreading scope: global (may be called from any thread).
- Automatically parallelized on domain level.
Radius of the circle.
Default value: 3
Suggested values: 3, 5, 6, 7, 8, 9, 10, 15
Number of checked neighbors on the circle.
Default value: 1
Suggested values: 1, 2, 3, 5
Threshold of grayvalue difference to each circle
point.
Default value: 15
Suggested values: 10, 15, 20, 25, 30, 35, 40, 45, 60, 80
Threshold of grayvalue difference to all circle points.
Default value: 30
Suggested values: 5, 10, 15, 20, 25, 30
Subpixel accuracy of point coordinates.
Default value:
'interpolation'
"interpolation"
"interpolation"
"interpolation"
"interpolation"
"interpolation"
List of values: 'interpolation'"interpolation""interpolation""interpolation""interpolation""interpolation", 'none'"none""none""none""none""none"
RowRowRowRowRowrow (output_control) point.y-array → HTupleHTupleHTupleVARIANTHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double) (Hlong / double) (Hlong / double)
Row-coordinates of the detected points.
Column-coordinates of the detected points.
gauss_filtergauss_filterGaussFiltergauss_filterGaussFilterGaussFilter
points_foerstnerpoints_foerstnerPointsFoerstnerpoints_foerstnerPointsFoerstnerPointsFoerstner,
points_harrispoints_harrisPointsHarrispoints_harrisPointsHarrisPointsHarris,
points_harris_binomialpoints_harris_binomialPointsHarrisBinomialpoints_harris_binomialPointsHarrisBinomialPointsHarrisBinomial,
points_sojkapoints_sojkaPointsSojkapoints_sojkaPointsSojkaPointsSojka
Foundation