points_lepetitT_points_lepetitPointsLepetitPointsLepetitpoints_lepetit (Operator)


points_lepetitT_points_lepetitPointsLepetitPointsLepetitpoints_lepetit — Detect points of interest using the Lepetit operator.


points_lepetit(Image : : Radius, CheckNeighbor, MinCheckNeighborDiff, MinScore, Subpix : Row, Column)

Herror T_points_lepetit(const Hobject Image, const Htuple Radius, const Htuple CheckNeighbor, const Htuple MinCheckNeighborDiff, const Htuple MinScore, const Htuple Subpix, Htuple* Row, Htuple* Column)

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 HImage::PointsLepetit(Hlong Radius, Hlong CheckNeighbor, Hlong MinCheckNeighborDiff, Hlong MinScore, const wchar_t* Subpix, HTuple* Row, HTuple* Column) const   (Windows only)

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)

def points_lepetit(image: HObject, radius: int, check_neighbor: int, min_check_neighbor_diff: int, min_score: int, subpix: str) -> Tuple[Sequence[Union[int, float]], Sequence[Union[int, float]]]


points_lepetitpoints_lepetitPointsLepetitPointsLepetitPointsLepetitpoints_lepetit 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 MinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffminCheckNeighborDiffmin_check_neighbor_diff. 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 CheckNeighborCheckNeighborCheckNeighborCheckNeighborcheckNeighborcheck_neighbor 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 MinScoreMinScoreMinScoreMinScoreminScoremin_score 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_lepetitPointsLepetitPointsLepetitPointsLepetitpoints_lepetit can especially be used for very fast interest point extraction. The results are however less robust than points extracted by points_harrispoints_harrisPointsHarrisPointsHarrisPointsHarrispoints_harris 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.

Execution Information


ImageImageImageImageimageimage (input_object)  singlechannelimage objectHImageHObjectHImageHobject (byte / uint2)

Input image.

RadiusRadiusRadiusRadiusradiusradius (input_control)  integer HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Radius of the circle.

Default value: 3

Suggested values: 3, 5, 6, 7, 8, 9, 10, 15

CheckNeighborCheckNeighborCheckNeighborCheckNeighborcheckNeighborcheck_neighbor (input_control)  integer HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Number of checked neighbors on the circle.

Default value: 1

Suggested values: 1, 2, 3, 5

MinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffMinCheckNeighborDiffminCheckNeighborDiffmin_check_neighbor_diff (input_control)  integer HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Threshold of gray value difference to each circle point.

Default value: 15

Suggested values: 10, 15, 20, 25, 30, 35, 40, 45, 60, 80

MinScoreMinScoreMinScoreMinScoreminScoremin_score (input_control)  integer HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Threshold of gray value difference to all circle points.

Default value: 30

Suggested values: 5, 10, 15, 20, 25, 30

SubpixSubpixSubpixSubpixsubpixsubpix (input_control)  string HTuplestrHTupleHtuple (string) (string) (HString) (char*)

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 HTupleSequence[Union[int, float]]HTupleHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double)

Row-coordinates of the detected points.

ColumnColumnColumnColumncolumncolumn (output_control)  point.x-array HTupleSequence[Union[int, float]]HTupleHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double)

Column-coordinates of the detected points.

Possible Predecessors



points_foerstnerpoints_foerstnerPointsFoerstnerPointsFoerstnerPointsFoerstnerpoints_foerstner, points_harrispoints_harrisPointsHarrisPointsHarrisPointsHarrispoints_harris, points_harris_binomialpoints_harris_binomialPointsHarrisBinomialPointsHarrisBinomialPointsHarrisBinomialpoints_harris_binomial, points_sojkapoints_sojkaPointsSojkaPointsSojkaPointsSojkapoints_sojka