add_texture_inspection_model_imageT_add_texture_inspection_model_imageAddTextureInspectionModelImageAddTextureInspectionModelImageadd_texture_inspection_model_image (Operator)

Name

add_texture_inspection_model_imageT_add_texture_inspection_model_imageAddTextureInspectionModelImageAddTextureInspectionModelImageadd_texture_inspection_model_image — Add training images to the texture inspection model.

Signature

add_texture_inspection_model_image(Image : : TextureInspectionModel : Indices)

Description

add_texture_inspection_model_imageadd_texture_inspection_model_imageAddTextureInspectionModelImageAddTextureInspectionModelImageadd_texture_inspection_model_image adds training images to the texture inspection model (TextureInspectionModelTextureInspectionModelTextureInspectionModeltextureInspectionModeltexture_inspection_model). The domain of the training images is considered in all further calculations. Since the feature extraction considers a certain neighborhood of each pixel, no features can be extracted for pixels at the border of the domain. The border size (Border) depends on the 'patch_size'"patch_size""patch_size""patch_size""patch_size" (set_texture_inspection_model_paramset_texture_inspection_model_paramSetTextureInspectionModelParamSetTextureInspectionModelParamset_texture_inspection_model_param) and computes to Border.

All images which are added to the texture inspection model are used within the training process (see train_texture_inspection_modeltrain_texture_inspection_modelTrainTextureInspectionModelTrainTextureInspectionModeltrain_texture_inspection_model for more information). Furthermore, it is possible to query all of the images passed to the texture inspection model with get_texture_inspection_model_imageget_texture_inspection_model_imageGetTextureInspectionModelImageGetTextureInspectionModelImageget_texture_inspection_model_image.

Every added image receives an index (IndicesIndicesIndicesindicesindices), which allows the user to generate an assignment between the added images and his image data. By calls of remove_texture_inspection_model_imageremove_texture_inspection_model_imageRemoveTextureInspectionModelImageRemoveTextureInspectionModelImageremove_texture_inspection_model_image, the index can further be used to delete images from the model that are not needed anymore.

It is possible to add either gray-scale images or multichannel images. However, all of the passed images should have the same number of channels.

For an explanation of the concept of the texture inspection see the introduction of chapter Inspection / Texture Inspection.

Execution Information

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Automatically parallelized on internal data level.

This operator modifies the state of the following input parameter:

TextureInspectionModelTextureInspectionModelTextureInspectionModeltextureInspectionModeltexture_inspection_model

During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.

Parameters

ImageImageImageimageimage (input_object) (multichannel-)image(-array) → object (byte / uint2 / real)

Image of flawless texture.

TextureInspectionModelTextureInspectionModelTextureInspectionModeltextureInspectionModeltexture_inspection_model (input_control, state is modified) texture_inspection_model → (handle)

Handle of the texture inspection model.

IndicesIndicesIndicesindicesindices (output_control) integer(-array) → (integer)

Indices of the images that have been added to the texture inspection model.

Example (HDevelop)

* Create texture inspection model
create_texture_inspection_model ('basic', TextureInspectionModel)
* Make this short example fast:
set_texture_inspection_model_param (TextureInspectionModel, \
                                    'gmm_em_max_iter', 1)
* Read and add training images
read_image (TrainImage, 'carpet/carpet_01')
add_texture_inspection_model_image (TrainImage, TextureInspectionModel, \
                                    Indices)
* Train the model
train_texture_inspection_model (TextureInspectionModel)
* Read and apply a test image
read_image (TrainImage, 'carpet/carpet_02')
apply_texture_inspection_model (TestImage, DefectCandidates, \
                                TextureInspectionModel, \
                                TextureInspectionResultID)

Result

The operator add_texture_inspection_model_imageadd_texture_inspection_model_imageAddTextureInspectionModelImageAddTextureInspectionModelImageadd_texture_inspection_model_image returns the value 2 ( H_MSG_TRUE) if the given parameters are valid and within acceptable range. Otherwise, an exception will be raised.

Possible Predecessors

create_texture_inspection_modelcreate_texture_inspection_modelCreateTextureInspectionModelCreateTextureInspectionModelcreate_texture_inspection_model, set_texture_inspection_model_paramset_texture_inspection_model_paramSetTextureInspectionModelParamSetTextureInspectionModelParamset_texture_inspection_model_param, get_texture_inspection_model_paramget_texture_inspection_model_paramGetTextureInspectionModelParamGetTextureInspectionModelParamget_texture_inspection_model_param

Possible Successors

Module

Matching

Operators