create_variation_modelT_create_variation_modelCreateVariationModelCreateVariationModel (Operator)

Name

create_variation_modelT_create_variation_modelCreateVariationModelCreateVariationModel — Create a variation model for image comparison.

Signature

create_variation_model( : : Width, Height, Type, Mode : ModelID)

Herror T_create_variation_model(const Htuple Width, const Htuple Height, const Htuple Type, const Htuple Mode, Htuple* ModelID)

void CreateVariationModel(const HTuple& Width, const HTuple& Height, const HTuple& Type, const HTuple& Mode, HTuple* ModelID)

void HVariationModel::HVariationModel(Hlong Width, Hlong Height, const HString& Type, const HString& Mode)

void HVariationModel::HVariationModel(Hlong Width, Hlong Height, const char* Type, const char* Mode)

void HVariationModel::HVariationModel(Hlong Width, Hlong Height, const wchar_t* Type, const wchar_t* Mode)   (Windows only)

void HVariationModel::CreateVariationModel(Hlong Width, Hlong Height, const HString& Type, const HString& Mode)

void HVariationModel::CreateVariationModel(Hlong Width, Hlong Height, const char* Type, const char* Mode)

void HVariationModel::CreateVariationModel(Hlong Width, Hlong Height, const wchar_t* Type, const wchar_t* Mode)   (Windows only)

static void HOperatorSet.CreateVariationModel(HTuple width, HTuple height, HTuple type, HTuple mode, out HTuple modelID)

public HVariationModel(int width, int height, string type, string mode)

void HVariationModel.CreateVariationModel(int width, int height, string type, string mode)

Description

create_variation_modelcreate_variation_modelCreateVariationModelCreateVariationModelCreateVariationModel creates a variation model that can be used for image comparison. The handle for the variation model is returned in ModelIDModelIDModelIDModelIDmodelID.

Typically, the variation model is used to discriminate correctly manufactured objects (“good objects”) from incorrectly manufactured objects (“bad objects”). It is assumed that the discrimination can be done solely based on the gray values of the object.

The variation model consists of an ideal image of the object to which the images of the objects to be tested are compared later on with compare_variation_modelcompare_variation_modelCompareVariationModelCompareVariationModelCompareVariationModel or compare_ext_variation_modelcompare_ext_variation_modelCompareExtVariationModelCompareExtVariationModelCompareExtVariationModel, and an image that represents the amount of gray value variation at every point of the object. The size of the images with which the object model is trained and with which the model is compared later on is passed in WidthWidthWidthWidthwidth and HeightHeightHeightHeightheight, respectively. The image type of the images used for training and comparison is passed in TypeTypeTypeTypetype.

The variation model is trained using multiple images of good objects. Therefore, it is essential that the training images show the objects in the same position and rotation. If this cannot be guarateed by external means, the pose of the object can, for example, be determined by using matching (see find_shape_modelfind_shape_modelFindShapeModelFindShapeModelFindShapeModel). The image can then be transformed to a reference pose with affine_trans_imageaffine_trans_imageAffineTransImageAffineTransImageAffineTransImage.

The parameter ModeModeModeModemode is used to determine how the image of the ideal object and the corresponding variation image are computed. For ModeModeModeModemode='standard'"standard""standard""standard""standard", the ideal image of the object is computed as the mean of all training images at the respective image positions. The corresponding variation image is computed as the standard deviation of the training images at the respective image positions. This mode has the advantage that the variation model can be trained iteratively, i.e., as soon as an image of a good object becomes available, it can be trained with train_variation_modeltrain_variation_modelTrainVariationModelTrainVariationModelTrainVariationModel. The disadvantage of this mode is that great care must be taken to ensure that only images of good objects are trained, because the mean and standard deviation are not robust against outliers, i.e., if an image of a bad object is trained inadvertently, the accuracy of the ideal object image and that of the variation image might be degraded.

If it cannot be avoided that the variation model is trained with some images of objects that can contain errors, ModeModeModeModemode can be set to 'robust'"robust""robust""robust""robust". In this mode, the image of the ideal object is computed as the median of all training images at the respective image positions. The corresponding variation image is computed as a suitably scaled median absolute deviation of the training images and the median image at the respective image positions. This mode has the advantage that it is robust against outliers. It has the disadvantage that it cannot be trained iteratively, i.e., all training images must be accumulated using concat_objconcat_objConcatObjConcatObjConcatObj and be trained with train_variation_modeltrain_variation_modelTrainVariationModelTrainVariationModelTrainVariationModel in a single call.

In some cases, it is impossible to acquire multiple training images. In this case, a useful variation image cannot be trained from the single training image. To solve this problem, variations of the training image can be created synthetically, e.g., by shifting the training image by pixel in the row and column directions or by using gray value morphology (e.g., gray_erosion_shapegray_erosion_shapeGrayErosionShapeGrayErosionShapeGrayErosionShape and gray_dilation_shapegray_dilation_shapeGrayDilationShapeGrayDilationShapeGrayDilationShape), and then training the synthetically modified images. A different possibility to create the variation model from a single image is to create the model with ModeModeModeModemode='direct'"direct""direct""direct""direct". In this case, the variation model can only be trained by specifying the ideal image and the variation image directly with prepare_direct_variation_modelprepare_direct_variation_modelPrepareDirectVariationModelPrepareDirectVariationModelPrepareDirectVariationModel. Since the variation typically is large at the edges of the object, edge operators like sobel_ampsobel_ampSobelAmpSobelAmpSobelAmp, edges_imageedges_imageEdgesImageEdgesImageEdgesImage, or gray_range_rectgray_range_rectGrayRangeRectGrayRangeRectGrayRangeRect should be used to create the variation image.

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

WidthWidthWidthWidthwidth (input_control)  extent.x HTupleHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Width of the images to be compared.

Default value: 640

Suggested values: 160, 192, 320, 384, 640, 768

HeightHeightHeightHeightheight (input_control)  extent.y HTupleHTupleHtuple (integer) (int / long) (Hlong) (Hlong)

Height of the images to be compared.

Default value: 480

Suggested values: 120, 144, 240, 288, 480, 576

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

Type of the images to be compared.

Default value: 'byte' "byte" "byte" "byte" "byte"

Suggested values: 'byte'"byte""byte""byte""byte", 'int2'"int2""int2""int2""int2", 'uint2'"uint2""uint2""uint2""uint2"

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

Method used for computing the variation model.

Default value: 'standard' "standard" "standard" "standard" "standard"

Suggested values: 'standard'"standard""standard""standard""standard", 'robust'"robust""robust""robust""robust", 'direct'"direct""direct""direct""direct"

ModelIDModelIDModelIDModelIDmodelID (output_control)  variation_model HVariationModel, HTupleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

ID of the variation model.

Complexity

A variation model created with create_variation_modelcreate_variation_modelCreateVariationModelCreateVariationModelCreateVariationModel requires 12*WidthWidthWidthWidthwidth*HeightHeightHeightHeightheight bytes of memory for ModeModeModeModemode = 'standard'"standard""standard""standard""standard" and ModeModeModeModemode = 'robust'"robust""robust""robust""robust" for TypeTypeTypeTypetype = 'byte'"byte""byte""byte""byte". For TypeTypeTypeTypetype = 'uint2'"uint2""uint2""uint2""uint2" and TypeTypeTypeTypetype = 'int2'"int2""int2""int2""int2", 14*WidthWidthWidthWidthwidth*HeightHeightHeightHeightheight are required. For ModeModeModeModemode = 'direct'"direct""direct""direct""direct" and after the training data has been cleared with clear_train_data_variation_modelclear_train_data_variation_modelClearTrainDataVariationModelClearTrainDataVariationModelClearTrainDataVariationModel, 2*WidthWidthWidthWidthwidth*HeightHeightHeightHeightheight bytes are required for TypeTypeTypeTypetype = 'byte'"byte""byte""byte""byte" and 4*WidthWidthWidthWidthwidth*HeightHeightHeightHeightheight for the other image types.

Result

create_variation_modelcreate_variation_modelCreateVariationModelCreateVariationModelCreateVariationModel returns 2 (H_MSG_TRUE) if all parameters are correct.

Possible Successors

train_variation_modeltrain_variation_modelTrainVariationModelTrainVariationModelTrainVariationModel, prepare_direct_variation_modelprepare_direct_variation_modelPrepareDirectVariationModelPrepareDirectVariationModelPrepareDirectVariationModel

See also

prepare_variation_modelprepare_variation_modelPrepareVariationModelPrepareVariationModelPrepareVariationModel, clear_variation_modelclear_variation_modelClearVariationModelClearVariationModelClearVariationModel, clear_train_data_variation_modelclear_train_data_variation_modelClearTrainDataVariationModelClearTrainDataVariationModelClearTrainDataVariationModel, find_shape_modelfind_shape_modelFindShapeModelFindShapeModelFindShapeModel, affine_trans_imageaffine_trans_imageAffineTransImageAffineTransImageAffineTransImage

Module

Matching