create_scaled_shape_modelCreateScaledShapeModelCreateScaledShapeModelcreate_scaled_shape_modelT_create_scaled_shape_model🔗

Short description🔗

create_scaled_shape_modelCreateScaledShapeModelCreateScaledShapeModelcreate_scaled_shape_modelT_create_scaled_shape_model — Prepare an isotropically scaled shape model for matching.

Signature🔗

create_scaled_shape_model( image Template, integer NumLevels, angle.rad AngleStart, angle.rad AngleExtent, angle.rad AngleStep, number ScaleMin, number ScaleMax, number ScaleStep, string Optimization, string Metric, number Contrast, number MinContrast, out shape_model ModelID )

Description🔗

The operator create_scaled_shape_modelCreateScaledShapeModel prepares a template, which is passed in the image Templatetemplatetemplate, as an isotropically scaled shape model used for matching. The ROI of the model is passed as the domain of Templatetemplatetemplate.

The output parameter ModelIDmodelIDmodel_id is a handle for this model, which is used in subsequent calls to find_scaled_shape_modelFindScaledShapeModel. The center of gravity of the domain (region) of the model image Templatetemplatetemplate is used as the origin (reference point) of the model. A different origin can be set with set_shape_model_originSetShapeModelOrigin. The model is generated using multiple image pyramid levels and is stored in memory. If a complete pregeneration of the model is selected (see below), the model is generated at multiple rotations and scales on each level. The model can be extended by clutter parameters with set_shape_model_clutterSetShapeModelClutter.

Input parameters in detail🔗

NumLevelsnumLevelsnum_levels: The number of pyramid levels is determined with the parameter NumLevelsnumLevelsnum_levels. 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, NumLevelsnumLevelsnum_levels must be chosen such that the model is still recognizable and contains a sufficient number of points (at least four) on the highest pyramid level. This can be checked using the output of inspect_shape_modelInspectShapeModel. 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_scaled_shape_modelCreateScaledShapeModel returns with an error message.

If NumLevelsnumLevelsnum_levels is set to 'auto'"auto" (or 00 for backwards compatibility), create_scaled_shape_modelCreateScaledShapeModel determines the number of pyramid levels automatically. The automatically computed number of pyramid levels can be queried using get_shape_model_paramsGetShapeModelParams. In rare cases, it might happen that create_scaled_shape_modelCreateScaledShapeModel 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 MinScoreminScoremin_score or Greedinessgreedinessgreediness in find_scaled_shape_modelFindScaledShapeModel 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_scaled_shape_modelFindScaledShapeModel may increase. In these cases, the number of pyramid levels should be selected using the output of inspect_shape_modelInspectShapeModel.
AngleStartangleStartangle_start, AngleExtentangleExtentangle_extent and AngleStepangleStepangle_step: The parameters AngleStartangleStartangle_start and AngleExtentangleExtentangle_extent 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_scaled_shape_modelFindScaledShapeModel. The parameter AngleStepangleStepangle_step determines the step length within the selected range of angles. Hence, if subpixel accuracy is not specified in find_scaled_shape_modelFindScaledShapeModel, this parameter specifies the accuracy that is achievable for the angles in find_scaled_shape_modelFindScaledShapeModel. AngleStepangleStepangle_step should be chosen based on the size of the object. Smaller models do not have many different discrete rotations in the image, and hence AngleStepangleStepangle_step should be chosen larger for smaller models. If AngleExtentangleExtentangle_extent is not an integer multiple of AngleStepangleStepangle_step, AngleStepangleStepangle_step is modified accordingly. To ensure that for model instances without rotation angle values of exactly 0.0 are returned by find_scaled_shape_modelFindScaledShapeModel, the range of possible rotations is modified as follows: If there is no positive integer value n such that AngleStartangleStartangle_start plus n times AngleStepangleStepangle_step is exactly 0.0, AngleStartangleStartangle_start is decreased by up to AngleStepangleStepangle_step and AngleExtentangleExtentangle_extent is increased by AngleStepangleStepangle_step.
ScaleMinscaleMinscale_min, ScaleMaxscaleMaxscale_max, and ScaleStepscaleStepscale_step: The parameters ScaleMinscaleMinscale_min and ScaleMaxscaleMaxscale_max determine the range of possible scales (sizes) of the model. A scale of 1 corresponds to the original size of the model. The parameter ScaleStepscaleStepscale_step determines the step length within the selected range of scales. Hence, if subpixel accuracy is not specified in find_scaled_shape_modelFindScaledShapeModel, this parameter specifies the accuracy that is achievable for the scales in find_scaled_shape_modelFindScaledShapeModel. Like AngleStepangleStepangle_step, ScaleStepscaleStepscale_step should be chosen based on the size of the object. If the range of scales is not an integer multiple of ScaleStepscaleStepscale_step, ScaleStepscaleStepscale_step is modified accordingly. To ensure that for model instances that are not scaled scale values of exactly 1.0 are returned by find_scaled_shape_modelFindScaledShapeModel, the range of possible scales is modified as follows: If there is no positive integer value n such that ScaleMinscaleMinscale_min plus n times ScaleStepscaleStepscale_step is exactly 1.0, ScaleMinscaleMinscale_min is decreased by up to ScaleStepscaleStepscale_step and ScaleMaxscaleMaxscale_max is increased such that the range of possible scales is increased by ScaleStepscaleStepscale_step.
Optimizationoptimizationoptimization: For particularly large models, it may be useful to reduce the number of model points by setting Optimizationoptimizationoptimization to a value different from 'none'"none". If Optimizationoptimizationoptimization \(=\) 'none'"none", all model points are stored. In all other cases, the number of points is reduced according to the value of Optimizationoptimizationoptimization. If the number of points is reduced, it may be necessary in find_scaled_shape_modelFindScaledShapeModel to set the parameter Greedinessgreedinessgreediness to a smaller value, e.g., 0.70.7 or 0.80.8. For small models, the reduction of the number of model points does not result in a speed-up of the search because in this case usually significantly more potential instances of the model must be examined.

If Optimizationoptimizationoptimization is set to 'auto'"auto", create_scaled_shape_modelCreateScaledShapeModel automatically determines the reduction of the number of model points.
Metricmetricmetric: The parameter Metricmetricmetric determines the conditions under which the model is recognized in the image.

If Metricmetricmetric \(=\) '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 Metricmetricmetric \(=\) '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_scaled_shape_modelFindScaledShapeModel will increase slightly in this case.

If Metricmetricmetric \(=\) 'ignore_local_polarity'"ignore_local_polarity", the model is found even if the contrast changes locally. This mode can, for example, be useful if the object consists of a part with medium gray value, within which either darker or brighter sub-objects lie. Since in this case the runtime of find_scaled_shape_modelFindScaledShapeModel increases significantly, it is usually better to create several models that reflect the possible contrast variations of the object with create_scaled_shape_modelCreateScaledShapeModel, and to match them simultaneously with find_scaled_shape_modelsFindScaledShapeModels.

The above three metrics can only be applied to single-channel images. If a multichannel image is used as the model image or as the search image, only the first channel will be used (and no error message will be returned).

If Metricmetricmetric \(=\) 'ignore_color_polarity'"ignore_color_polarity", the model is found even if the color contrast changes locally. This is, for example, the case if parts of the object can change their color, e.g., from red to green. In particular, this mode is useful if it is not known in advance in which channels the object is visible. In this mode, the runtime of find_scaled_shape_modelFindScaledShapeModel can also increase significantly. The metric 'ignore_color_polarity'"ignore_color_polarity" can be used for images with an arbitrary number of channels. If it is used for single-channel images it has the same effect as 'ignore_local_polarity'"ignore_local_polarity". It should be noted that for Metricmetricmetric \(=\) 'ignore_color_polarity'"ignore_color_polarity" the number of channels in the model creation with create_scaled_shape_modelCreateScaledShapeModel and in the search with find_scaled_shape_modelFindScaledShapeModel can be different. This can, for example, be used to create a model from a synthetically generated single-channel image. Furthermore, it should be noted that the channels do not need to contain a spectral subdivision of the light (like in an RGB image). The channels can, for example, also contain images of the same object that were obtained by illuminating the object from different directions.
Contrastcontrastcontrast: The parameter Contrastcontrastcontrast determines the contrast the model points must have. The contrast is a measure for local gray value differences between the object and the background and between different parts of the object. Contrastcontrastcontrast should be chosen such that only the significant features of the template are used for the model. Contrastcontrastcontrast can also contain a tuple with two values. In this case, the model is segmented using a method similar to the hysteresis threshold method used in edges_imageEdgesImage. Here, the first element of the tuple determines the lower threshold, while the second element determines the upper threshold. For more information about the hysteresis threshold method, see hysteresis_thresholdHysteresisThreshold. Optionally, Contrastcontrastcontrast can contain a third value as the last element of the tuple. This value determines a threshold for the selection of significant model components based on the size of the components, i.e., components that have fewer points than the minimum size thus specified are suppressed. As the minimum size is applied on the extent of the components, the derived model contours can still be smaller than the specified minimum size. This threshold for the minimum size is divided by two for each successive pyramid level. If small model components should be suppressed, but hysteresis thresholding should not be performed, nevertheless three values must be specified in Contrastcontrastcontrast. In this case, the first two values can simply be set to identical values. The effect of this parameter can be checked in advance with inspect_shape_modelInspectShapeModel.

If Contrastcontrastcontrast is set to 'auto'"auto", create_scaled_shape_modelCreateScaledShapeModel determines the three above described values automatically. Besides, only the contrast ('auto_contrast'"auto_contrast"), the hysteresis thresholds ('auto_contrast_hyst'"auto_contrast_hyst"), or the minimum size ('auto_min_size'"auto_min_size") can be determined automatically. The remaining values that are not determined automatically can additionally be passed in the form of a tuple. Also various combinations are allowed: If, for example, ['auto_contrast', 'auto_min_size']["auto_contrast", "auto_min_size"] is passed, both the contrast and the minimum size are determined automatically. If ['auto_min_size', 20, 30]["auto_min_size", 20, 30] is passed, the minimum size is determined automatically while the hysteresis thresholds are set to 2020 and 3030, etc. In certain cases, it might happen that the automatic determination of the contrast thresholds is not satisfying. For example, a manual setting of these parameters should be preferred if certain model components should be included or suppressed because of application-specific reasons or if the object contains several different contrasts. Therefore, the contrast thresholds should be automatically determined with determine_shape_model_paramsDetermineShapeModelParams and subsequently verified using inspect_shape_modelInspectShapeModel before calling create_scaled_shape_modelCreateScaledShapeModel. Note that MinContrastminContrastmin_contrast influences the automatic contrast estimation, and hence also the estimation of the minimum size.
MinContrastminContrastmin_contrast: With MinContrastminContrastmin_contrast, it can be determined which contrast the model must at least have in the recognition performed by find_scaled_shape_modelFindScaledShapeModel. In other words, this parameter separates the model from the noise in the image. Therefore, a good choice is the range of gray value changes caused by the noise in the image. If, for example, the gray values fluctuate within a range of 10 gray levels, MinContrastminContrastmin_contrast should be set to 10. If multichannel images are used for the model and the search images, and if the parameter Metricmetricmetric is set to 'ignore_color_polarity'"ignore_color_polarity" (see above) the noise in one channel must be multiplied by the square root of the number of channels to determine MinContrastminContrastmin_contrast. If, for example, the gray values fluctuate within a range of 10 gray levels in a single channel and the image is a three-channel image MinContrastminContrastmin_contrast should be set to 17. Obviously, MinContrastminContrastmin_contrast must be smaller than Contrastcontrastcontrast. If the model should be recognized in very low contrast images, MinContrastminContrastmin_contrast must be set to a correspondingly small value. If the model should be recognized even if it is severely occluded, MinContrastminContrastmin_contrast should be slightly larger than the range of gray value fluctuations created by noise in order to ensure that the position and rotation of the model are extracted robustly and accurately by find_scaled_shape_modelFindScaledShapeModel.

If MinContrastminContrastmin_contrast is set to 'auto'"auto", the minimum contrast is determined automatically based on the noise in the model image. Consequently, an automatic determination only makes sense if the image noise during the recognition is similar to the noise in the model image. Furthermore, in some cases it is advisable to increase the automatically determined value in order to increase the robustness against occlusions (see above). The automatically computed minimum contrast can be queried using get_shape_model_paramsGetShapeModelParams.

Complete pregeneration of the model🔗

Optionally, a second value can be passed in Optimizationoptimizationoptimization. This value determines whether the model is pregenerated completely or not. To do so, the second value of Optimizationoptimizationoptimization must be set to either 'pregeneration'"pregeneration" or 'no_pregeneration'"no_pregeneration". If the second value is not used (i.e., if only one value is passed), the mode that is set with set_system('pregenerate_shape_models',...) is used. With the default value ('pregenerate_shape_models'"pregenerate_shape_models" \(=\) 'false'"false"), the model is not pregenerated completely. The complete pregeneration of the model normally leads to slightly lower runtimes because the model does not need to be transformed at runtime. However, in this case, the memory requirements and the time required to create the model are significantly higher. It should also be noted that it cannot be expected that the two modes return exactly identical results because transforming the model at runtime necessarily leads to different internal data for the transformed models than pregenerating the transformed models. For example, if the model is not pregenerated completely, find_scaled_shape_modelFindScaledShapeModel typically returns slightly lower scores, which may require setting a slightly lower value for MinScoreminScoremin_score than for a completely pregenerated model. Furthermore, the poses obtained by interpolation may differ slightly in the two modes. If maximum accuracy is desired, the pose of the model should be determined by least-squares adjustment.

If a complete pregeneration of the model is selected, the model is pregenerated for the selected angle and scale range and stored in memory. The memory required to store the model is proportional to the number of angle steps, the number of scale steps, and the number of points in the model. Hence, if AngleStepangleStepangle_step or ScaleStepscaleStepscale_step are too small or AngleExtentangleExtentangle_extent or the range of scales are too big, it may happen that the model no longer fits into the (virtual) memory. In this case, either AngleStepangleStepangle_step or ScaleStepscaleStepscale_step must be enlarged or AngleExtentangleExtentangle_extent or the range of scales 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_scaled_shape_modelFindScaledShapeModel, AngleStep >= 1° and ScaleStep >= 0.02 can be selected for models of a diameter smaller than about 200 pixels.

If AngleStepangleStepangle_step = 'auto'"auto" or ScaleStepscaleStepscale_step = 'auto'"auto" (or 00 for backwards compatibility in both cases) is selected, create_scaled_shape_modelCreateScaledShapeModel automatically determines a suitable angle or scale step length, respectively, based on the size of the model. The automatically computed angle and scale step lengths can be queried using get_shape_model_paramsGetShapeModelParams.

If a complete pregeneration of the model is not selected, the model is only created in a reference pose on each pyramid level. In this case, the model must be transformed to the different angles and scales at runtime in find_scaled_shape_modelFindScaledShapeModel. Because of this, the recognition of the model might require slightly more time.

Note that pregenerated shape models are tailored to a specific image size. For runtime reasons using images of different sizes during the search with the same model in parallel is not supported. In this case, copies of the same model must be used, otherwise the program may crash!

Execution information🔗

Execution information

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Processed without parallelization.

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🔗

Templatetemplatetemplate (input_object) (multichannel-)image → object (byte / uint2)HObject (byte / uint2)HImage (byte / uint2)HObject (byte / uint2)Hobject (byte / uint2)

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

NumLevelsnumLevelsnum_levels (input_control) integer → (integer / string)HTuple (Hlong / HString)HTuple (int / long / string)Union[int, str]Htuple (Hlong / char*)

Maximum number of pyramid levels.

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

AngleStartangleStartangle_start (input_control) angle.rad → (real)HTuple (double)HTuple (double)floatHtuple (double)

Smallest rotation of the pattern.

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

AngleExtentangleExtentangle_extent (input_control) angle.rad → (real)HTuple (double)HTuple (double)floatHtuple (double)

Extent of the rotation angles.

Default: 0.790.79
Suggested values: 6.29, 3.14, 1.57, 0.79, 0.396.29, 3.14, 1.57, 0.79, 0.39
Restriction: AngleExtent >= 0

AngleStepangleStepangle_step (input_control) angle.rad → (real / string)HTuple (double / HString)HTuple (double / string)Union[float, str]Htuple (double / char*)

Step length of the angles (resolution).

Default: 'auto'"auto"
Suggested values: 'auto', 0.0175, 0.0349, 0.0524, 0.0698, 0.0873
Restriction: AngleStep >= 0 && AngleStep <= pi/2

ScaleMinscaleMinscale_min (input_control) number → (real)HTuple (double)HTuple (double)floatHtuple (double)

Minimum scale of the pattern.

Default: 0.90.9
Suggested values: 0.5, 0.6, 0.7, 0.8, 0.9, 1.00.5, 0.6, 0.7, 0.8, 0.9, 1.0
Restriction: ScaleMin > 0

ScaleMaxscaleMaxscale_max (input_control) number → (real)HTuple (double)HTuple (double)floatHtuple (double)

Maximum scale of the pattern.

Default: 1.11.1
Suggested values: 1.0, 1.1, 1.2, 1.3, 1.4, 1.51.0, 1.1, 1.2, 1.3, 1.4, 1.5
Restriction: ScaleMax >= ScaleMin

ScaleStepscaleStepscale_step (input_control) number → (real / string)HTuple (double / HString)HTuple (double / string)Union[float, str]Htuple (double / char*)

Scale step length (resolution).

Default: 'auto'"auto"
Suggested values: 'auto', 0.01, 0.02, 0.05, 0.1, 0.15, 0.2
Restriction: ScaleStep >= 0

Optimizationoptimizationoptimization (input_control) string(-array) → (string)HTuple (HString)HTuple (string)MaybeSequence[str]Htuple (char*)

Kind of optimization and optionally method used for generating the model.

Default: 'auto'"auto"
List of values: 'auto', 'no_pregeneration', 'none', 'point_reduction_high', 'point_reduction_low', 'point_reduction_medium', 'pregeneration'

Metricmetricmetric (input_control) string → (string)HTuple (HString)HTuple (string)strHtuple (char*)

Match metric.

Default: 'use_polarity'"use_polarity"
List of values: 'ignore_color_polarity', 'ignore_global_polarity', 'ignore_local_polarity', 'use_polarity'

Contrastcontrastcontrast (input_control) number(-array) → (integer / string)HTuple (Hlong / HString)HTuple (int / long / string)MaybeSequence[Union[int, str]]Htuple (Hlong / char*)

Threshold or hysteresis thresholds for the contrast of the object in the template image and optionally minimum size of the object parts.

Default: 'auto'"auto"
Suggested values: 'auto', 'auto_contrast', 'auto_contrast_hyst', 'auto_min_size', 10, 20, 30, 40, 60, 80, 100, 120, 140, 160

MinContrastminContrastmin_contrast (input_control) number → (integer / string)HTuple (Hlong / HString)HTuple (int / long / string)Union[int, str]Htuple (Hlong / char*)

Minimum contrast of the objects in the search images.

Default: 'auto'"auto"
Suggested values: 'auto', 1, 2, 3, 5, 7, 10, 20, 30, 40"auto", 1, 2, 3, 5, 7, 10, 20, 30, 40
Restriction: MinContrast < Contrast

ModelIDmodelIDmodel_id (output_control) shape_model → (handle)HTuple (HHandle)HShapeModel, HTuple (IntPtr)HHandleHtuple (handle)

Handle of the model.

Result🔗

If the parameters are valid, the operator create_scaled_shape_modelCreateScaledShapeModel returns the value 2 (H_MSG_TRUE). If necessary an exception is raised. If the parameters NumLevelsnumLevelsnum_levels and Contrastcontrastcontrast are chosen such that the model contains too few points, the error 8510 is raised.

Combinations with other operators🔗

Combinations

Possible predecessors

draw_regionDrawRegion, reduce_domainReduceDomain, thresholdThreshold

Possible successors

find_scaled_shape_modelFindScaledShapeModel, find_scaled_shape_modelsFindScaledShapeModels, get_shape_model_paramsGetShapeModelParams, clear_shape_modelClearShapeModel, write_shape_modelWriteShapeModel, set_shape_model_originSetShapeModelOrigin, set_shape_model_clutterSetShapeModelClutter

Alternatives

create_generic_shape_modelCreateGenericShapeModel

Module🔗

Matching