Operator Reference
prepare_direct_variation_model (Operator)
prepare_direct_variation_model — Prepare a variation model for comparison with an image.
Signature
prepare_direct_variation_model(RefImage, VarImage : : ModelID, AbsThreshold, VarThreshold : )
Description
prepare_direct_variation_model prepares a variation model
for the image comparison with compare_variation_model or
compare_ext_variation_model. The variation model must have
been created with Mode='direct' with
create_variation_model. In contrast to
prepare_variation_model, the ideal image of the object and
the corresponding variation image are not computed with
train_variation_model, but are specified directly in
RefImage and VarImage. This is useful if the
variation model should be created from a single image, as described
with create_variation_model. The variation image should
typically be created with edge operators like sobel_amp,
edges_image, or gray_range_rect.
prepare_direct_variation_model converts the ideal image
RefImage and the variation image VarImage into two
threshold images and stores them in the variation model. These
threshold images are used in compare_variation_model or
compare_ext_variation_model to perform the comparison of
the current image to the variation model.
Two thresholds are used to compute the threshold images. The
parameter AbsThreshold determines the minimum amount of
gray levels by which the image of the current object must differ
from the image of the ideal object. The parameter
VarThreshold determines a factor relative to the variation
image for the minimum difference of the current image and the ideal
image.
VarThreshold utilizes VarImage to define regions,
in which differences in gray values may occur which should not be
counted as errors.
This allows variations for specific parts of the object to inspect.
AbsThreshold and VarThreshold each can
contain one or two values. If two values are specified, different
thresholds can be determined for too bright and too dark pixels. In
this mode, the first value refers to too bright pixels, while the
second value refers to too dark pixels. If one value is specified,
this value refers to both the too bright and too dark pixels. Let
i(x,y) be the ideal image RefImage,
v(x,y) the variation image VarImage,
,
,
,
and
(or ,
,
, and
,
respectively). Then the two threshold images
are computed as follows:
If the current image c(x,y) is compared to the
variation model using compare_variation_model, the output
region contains all points that differ substantially from the model,
i.e., that fulfill the following condition:
In compare_ext_variation_model, extended comparison modes
are available, which return only too bright errors, only too dark
errors, or bright and dark errors as separate regions.
After the threshold images have been created they can be read out
with get_thresh_images_variation_model.
It should be noted that RefImage and VarImage are
not stored as the ideal and variation images in the model to save
memory in the model.
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 modifies the state of the following input parameter:
During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.
Parameters
RefImage (input_object) singlechannelimage → object (byte / int2 / uint2)
Reference image of the object.
VarImage (input_object) singlechannelimage → object (byte / int2 / uint2)
Variation image of the object.
ModelID (input_control, state is modified) variation_model → (handle)
ID of the variation model.
AbsThreshold (input_control) number(-array) → (real / integer)
Absolute minimum threshold for the differences between the image and the variation model.
Default: 10
Suggested values: 0, 5, 10, 15, 20, 30, 40, 50
Restriction:
AbsThreshold >= 0
VarThreshold (input_control) number(-array) → (real / integer)
Threshold for the differences based on the variation of the variation model.
Default: 2
Suggested values: 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5
Restriction:
VarThreshold >= 0
Example (HDevelop)
read_image (Image, 'model') sobel_amp (Image, VarImage, 'sum_abs', 3) get_image_pointer1 (Image, Pointer, Type, Width, Height) create_variation_model (Width, Height, Type, 'direct', ModelID) prepare_direct_variation_model (Image, VarImage, ModelID, 20, 1) write_variation_model (ModelID, 'model.var')
Result
prepare_direct_variation_model returns 2 (
H_MSG_TRUE)
if all
parameters are correct.
Possible Predecessors
sobel_amp,
edges_image,
gray_range_rect
Possible Successors
compare_variation_model,
compare_ext_variation_model,
get_thresh_images_variation_model,
write_variation_model
Alternatives
See also
Module
Matching