create_ncc_modelT_create_ncc_modelCreateNccModelCreateNccModel (Operator)

Name

create_ncc_modelT_create_ncc_modelCreateNccModelCreateNccModel — Prepare an NCC model for matching.

Signature

create_ncc_model(Template : : NumLevels, AngleStart, AngleExtent, AngleStep, Metric : ModelID)

Herror T_create_ncc_model(const Hobject Template, const Htuple NumLevels, const Htuple AngleStart, const Htuple AngleExtent, const Htuple AngleStep, const Htuple Metric, Htuple* ModelID)

void CreateNccModel(const HObject& Template, const HTuple& NumLevels, const HTuple& AngleStart, const HTuple& AngleExtent, const HTuple& AngleStep, const HTuple& Metric, HTuple* ModelID)

void HNCCModel::HNCCModel(const HImage& Template, const HTuple& NumLevels, double AngleStart, double AngleExtent, const HTuple& AngleStep, const HString& Metric)

void HNCCModel::HNCCModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const HString& Metric)

void HNCCModel::HNCCModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const char* Metric)

void HNCCModel::HNCCModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const wchar_t* Metric)   (Windows only)

void HNCCModel::CreateNccModel(const HImage& Template, const HTuple& NumLevels, double AngleStart, double AngleExtent, const HTuple& AngleStep, const HString& Metric)

void HNCCModel::CreateNccModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const HString& Metric)

void HNCCModel::CreateNccModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const char* Metric)

void HNCCModel::CreateNccModel(const HImage& Template, Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const wchar_t* Metric)   (Windows only)

HNCCModel HImage::CreateNccModel(const HTuple& NumLevels, double AngleStart, double AngleExtent, const HTuple& AngleStep, const HString& Metric) const

HNCCModel HImage::CreateNccModel(Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const HString& Metric) const

HNCCModel HImage::CreateNccModel(Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const char* Metric) const

HNCCModel HImage::CreateNccModel(Hlong NumLevels, double AngleStart, double AngleExtent, double AngleStep, const wchar_t* Metric) const   (Windows only)

static void HOperatorSet.CreateNccModel(HObject template, HTuple numLevels, HTuple angleStart, HTuple angleExtent, HTuple angleStep, HTuple metric, out HTuple modelID)

public HNCCModel(HImage template, HTuple numLevels, double angleStart, double angleExtent, HTuple angleStep, string metric)

public HNCCModel(HImage template, int numLevels, double angleStart, double angleExtent, double angleStep, string metric)

void HNCCModel.CreateNccModel(HImage template, HTuple numLevels, double angleStart, double angleExtent, HTuple angleStep, string metric)

void HNCCModel.CreateNccModel(HImage template, int numLevels, double angleStart, double angleExtent, double angleStep, string metric)

HNCCModel HImage.CreateNccModel(HTuple numLevels, double angleStart, double angleExtent, HTuple angleStep, string metric)

HNCCModel HImage.CreateNccModel(int numLevels, double angleStart, double angleExtent, double angleStep, string metric)

Description

The operator create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel prepares a template, which is passed in the image TemplateTemplateTemplateTemplatetemplate, as an NCC model used for matching using the normalized cross correlation (NCC). The ROI of the model is passed as the domain of TemplateTemplateTemplateTemplatetemplate.

The model is generated using multiple image pyramid levels at multiple rotations on each level and is stored in memory. The output parameter ModelIDModelIDModelIDModelIDmodelID is a handle for this model, which is used in subsequent calls to find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel.

The number of pyramid levels is determined with the parameter NumLevelsNumLevelsNumLevelsNumLevelsnumLevels. It should be chosen as large as possible because by this the time necessary to find the object is significantly reduced. On the other hand, NumLevelsNumLevelsNumLevelsNumLevelsnumLevels must be chosen such that the model is still recognizable and contains a sufficient number of points (at least eight) on the highest pyramid level. This can be checked using the domains of the output images of gen_gauss_pyramidgen_gauss_pyramidGenGaussPyramidGenGaussPyramidGenGaussPyramid. If not enough model points are generated, the number of pyramid levels is reduced internally until enough model points are found on the highest pyramid level. If this procedure would lead to a model with no pyramid levels, i.e., if the number of model points is already too small on the lowest pyramid level, create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel returns an error message. If NumLevelsNumLevelsNumLevelsNumLevelsnumLevels is set to 'auto'"auto""auto""auto""auto" or 0, create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel determines the number of pyramid levels automatically. The automatically computed number of pyramid levels can be queried using get_ncc_model_paramsget_ncc_model_paramsGetNccModelParamsGetNccModelParamsGetNccModelParams. In rare cases, it might happen that create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel determines a value for the number of pyramid levels that is too large or too small. If the number of pyramid levels is chosen too large, the model may not be recognized in the image or it may be necessary to select very low parameters for MinScore in find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel in order to find the model. If the number of pyramid levels is chosen too small, the time required to find the model in find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel may increase. In these cases, the number of pyramid levels should be selected by inspecting the output of gen_gauss_pyramidgen_gauss_pyramidGenGaussPyramidGenGaussPyramidGenGaussPyramid. Here, Mode = 'constant'"constant""constant""constant""constant" and Scale = 0.5 should be used.

The parameters AngleStartAngleStartAngleStartAngleStartangleStart and AngleExtentAngleExtentAngleExtentAngleExtentangleExtent determine the range of possible rotations, in which the model can occur in the image. Note that the model can only be found in this range of angles by find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel. The parameter AngleStepAngleStepAngleStepAngleStepangleStep determines the step length within the selected range of angles. Hence, if subpixel accuracy is not specified in find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel, this parameter specifies the accuracy that is achievable for the angles in find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel. AngleStepAngleStepAngleStepAngleStepangleStep should be chosen based on the size of the object. Smaller models do not possess many different discrete rotations in the image, and hence AngleStepAngleStepAngleStepAngleStepangleStep should be chosen larger for smaller models. If AngleExtentAngleExtentAngleExtentAngleExtentangleExtent is not an integer multiple of AngleStepAngleStepAngleStepAngleStepangleStep, AngleStepAngleStepAngleStepAngleStepangleStep is modified accordingly. To ensure a sampling of the range of possible rotations that is independent of the given AngleStartAngleStartAngleStartAngleStartangleStart, the range of possible rotations is modified as follows: If there is no positive integer value n such that AngleStartAngleStartAngleStartAngleStartangleStart plus n times AngleStepAngleStepAngleStepAngleStepangleStep is exactly 0.0, AngleStartAngleStartAngleStartAngleStartangleStart is decreased by up to AngleStepAngleStepAngleStepAngleStepangleStep and AngleExtentAngleExtentAngleExtentAngleExtentangleExtent is increased by AngleStepAngleStepAngleStepAngleStepangleStep.

The model is pre-generated for the selected angle range and stored in memory. The memory required to store the model is proportional to the number of angle steps and the number of points in the model. Hence, if AngleStepAngleStepAngleStepAngleStepangleStep is too small or AngleExtentAngleExtentAngleExtentAngleExtentangleExtent too big, it may happen that the model no longer fits into the (virtual) memory. In this case, either AngleStepAngleStepAngleStepAngleStepangleStep must be enlarged or AngleExtentAngleExtentAngleExtentAngleExtentangleExtent must be reduced. In any case, it is desirable that the model completely fits into the main memory, because this avoids paging by the operating system, and hence the time to find the object will be much smaller. Since angles can be determined with subpixel resolution by find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel, AngleStepAngleStepAngleStepAngleStepangleStep >= 1 can be selected for models of a diameter smaller than about 200 pixels. If AngleStepAngleStepAngleStepAngleStepangleStep = 'auto'"auto""auto""auto""auto" or 0 is selected, create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel automatically determines a suitable angle step length based on the size of the model. The automatically computed angle step length can be queried using get_ncc_model_paramsget_ncc_model_paramsGetNccModelParamsGetNccModelParamsGetNccModelParams.

The parameter MetricMetricMetricMetricmetric determines the conditions under which the model is recognized in the image. If MetricMetricMetricMetricmetric = 'use_polarity'"use_polarity""use_polarity""use_polarity""use_polarity", the object in the image and the model must have the same contrast. If, for example, the model is a bright object on a dark background, the object is found only if it is also brighter than the background. If MetricMetricMetricMetricmetric = 'ignore_global_polarity'"ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity", the object is found in the image also if the contrast reverses globally. In the above example, the object hence is also found if it is darker than the background. The runtime of find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel will increase slightly in this case.

The center of gravity of the domain (region) of the model image TemplateTemplateTemplateTemplatetemplate is used as the origin (reference point) of the model. A different origin can be set with set_ncc_model_originset_ncc_model_originSetNccModelOriginSetNccModelOriginSetNccModelOrigin.

Execution Information

This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.

Parameters

TemplateTemplateTemplateTemplatetemplate (input_object)  singlechannelimage objectHImageHImageHobject (byte / uint2)

Input image whose domain will be used to create the model.

NumLevelsNumLevelsNumLevelsNumLevelsnumLevels (input_control)  integer HTupleHTupleHtuple (integer / string) (int / long / string) (Hlong / HString) (Hlong / char*)

Maximum number of pyramid levels.

Default value: 'auto' "auto" "auto" "auto" "auto"

List of values: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 'auto'"auto""auto""auto""auto"

AngleStartAngleStartAngleStartAngleStartangleStart (input_control)  angle.rad HTupleHTupleHtuple (real) (double) (double) (double)

Smallest rotation of the pattern.

Default value: -0.39

Suggested values: -3.14, -1.57, -0.79, -0.39, -0.20, 0.0

AngleExtentAngleExtentAngleExtentAngleExtentangleExtent (input_control)  angle.rad HTupleHTupleHtuple (real) (double) (double) (double)

Extent of the rotation angles.

Default value: 0.79

Suggested values: 6.29, 3.14, 1.57, 0.79, 0.39

Restriction: AngleExtent >= 0

AngleStepAngleStepAngleStepAngleStepangleStep (input_control)  angle.rad HTupleHTupleHtuple (real / string) (double / string) (double / HString) (double / char*)

Step length of the angles (resolution).

Default value: 'auto' "auto" "auto" "auto" "auto"

Suggested values: 'auto'"auto""auto""auto""auto", 0.0, 0.0175, 0.0349, 0.0524, 0.0698, 0.0873

Restriction: AngleStep >= 0 && AngleStep <= pi / 16

MetricMetricMetricMetricmetric (input_control)  string HTupleHTupleHtuple (string) (string) (HString) (char*)

Match metric.

Default value: 'use_polarity' "use_polarity" "use_polarity" "use_polarity" "use_polarity"

List of values: 'ignore_global_polarity'"ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity", 'use_polarity'"use_polarity""use_polarity""use_polarity""use_polarity"

ModelIDModelIDModelIDModelIDmodelID (output_control)  ncc_model HNCCModel, HTupleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Handle of the model.

Result

If the parameters are valid, the operator create_ncc_modelcreate_ncc_modelCreateNccModelCreateNccModelCreateNccModel returns the value 2 (H_MSG_TRUE). If the parameter NumLevelsNumLevelsNumLevelsNumLevelsnumLevels are chosen such that the model contains too few points, the error 8506 is raised.

Possible Predecessors

draw_regiondraw_regionDrawRegionDrawRegionDrawRegion, reduce_domainreduce_domainReduceDomainReduceDomainReduceDomain, thresholdthresholdThresholdThresholdThreshold

Possible Successors

find_ncc_modelfind_ncc_modelFindNccModelFindNccModelFindNccModel, get_ncc_model_paramsget_ncc_model_paramsGetNccModelParamsGetNccModelParamsGetNccModelParams, clear_ncc_modelclear_ncc_modelClearNccModelClearNccModelClearNccModel, write_ncc_modelwrite_ncc_modelWriteNccModelWriteNccModelWriteNccModel, set_ncc_model_originset_ncc_model_originSetNccModelOriginSetNccModelOriginSetNccModelOrigin, set_ncc_model_paramset_ncc_model_paramSetNccModelParamSetNccModelParamSetNccModelParam, find_ncc_modelsfind_ncc_modelsFindNccModelsFindNccModelsFindNccModels

Alternatives

create_shape_modelcreate_shape_modelCreateShapeModelCreateShapeModelCreateShapeModel, create_scaled_shape_modelcreate_scaled_shape_modelCreateScaledShapeModelCreateScaledShapeModelCreateScaledShapeModel, create_aniso_shape_modelcreate_aniso_shape_modelCreateAnisoShapeModelCreateAnisoShapeModelCreateAnisoShapeModel

Module

Matching