创建组件识别数据的方法.pdf - 第169页

169/178 IM-SMT-VSNDI C-0002 -000 << Items to be set for Cor ner detection >> Shape T ype Cor ner Surface type Selects f rom Reflecting / Non r eflecting Algorithm T ype Norm al Mark Threshold Sets the binariz…

100%1 / 178
168/178
IM-SMT-VSNDIC-0002-000
distribution on the straight lines, then the detailed matching is performed by using those
positions as the center.
As speeding up process is not adopted for “PTRN Whole” mode, it takes time for processing
compare to other modes. However, there is the least possibility for the detection error and it
provides the high detection accuracy.
The matching degree is calculated by normalized correlation. Therefore the overall fluctuation
in brightness does not affect the degree.
The matching degree decreases when unevenness of lighting or reflection fluctuates.
Also it does not correspond to the size variation and rotation (as it may decrease the matching
degree), it is not applicable for the objects that change size or rotate.
<< Items to be set for Matching detection >>
Shape Type --
Surface type --
Algorithm Type Selects from “PTRN Outline” ,”PTRN GrayLev” or “PTRN Whole”
Mark Threshold
--
Tolerance
Specifies the allowable matching level. When the matching level
is more than (1.0 – tolerance /100), it is determined to be
satisfactory.
Search Area Sets the detection range.
Cut Inner Noise
--
Cut Outer
Noise
--
Pattern Size X Template size X
Pattern Size Y Template size Y
Offset X Offset amount X from the center of the template
Offset Y Offset amount Y from the center of the template
Table 115
3.3 Corner detection
With this recognition method, the linear elements are detected from the contour of the object
with the largest surface area, and from those elements, those that are thought to be corners
are detected and recognized.
Caution:
In this mode, recognition should be performed only when there is only one corner in the
detection range.
If there are more than one corner in the detection range, it is impossible to determine which
coordinate of the corner to be detected.
Figure 138
169/178
IM-SMT-VSNDIC-0002-000
<< Items to be set for Corner detection >>
Shape Type Corner
Surface type Selects from Reflecting / Non reflecting
Algorithm Type Normal
Mark Threshold
Sets the binarization level.
(When 0 is specified, binarization level is set automatically.
Tolerance --
Search Area Sets the detection range.
Cut Inner Noise Selects from 0 through 9.
Cut Outer Noise Selects from 0 through 9.
Mark Outsize
Specifies the length of the segment targeted for processing
(the dimension line in
Figure 138
).
Only items with a segment equal to or longer than the value
specified here is targeted for processing.
If this is set to 0, all segments are targeted for processing.
Table 116
3.4. Top Edge detection
With this recognition method, the linear elements are detected from the contour of the object
with the largest surface area, and from those elements, those that are thought to be tips are
detected and recognized.
Caution:
In this mode, recognition should be performed only when there is only one tip in the detection
range.
If there are more than one tip in the detection range, it is impossible to determine which
coordinate of the tip to be detected.
Figure 139
<< Items to be set for Top Edge detection >>
Shape Type Tip detection
Surface type Selects from Reflect / Non reflect
Algorithm Type Normal
Mark Threshold
Sets the binarization level. (When 0 is specified, binarization level
is set automatically.
Tolerance Sets the tolerance of the tip width (specified by the Mark Outsize)
Search Area Sets the detection range.
Cut Inner Noise Selects from 0 through 9.
Cut Outer Noise Selects from 0 through 9.
Mark Outsize Sets the width of the tip portion. (The dimension line in
Figure 139.)
Table 117
170/178
IM-SMT-VSNDIC-0002-000
3.5. CirEdge detection
With this recognition method, the circular elements are detected from the contour of the
object with the largest surface area, and from those elements, those that are thought to be
circles are detected and recognized. As presumed circles are recognized, it is possible to
perform recognition in case a part of the contour is missing.
However, depends on the software version, when the missing part of the object is large, it
may not be able to be recognized as the surface area and shape constant are checked before
the contour of the circle is presumed. (Please refer to “3.1.
Center of Gravity detection
(Recognition type: Normal)
”.) “Edge circle detection” should be used for these objects.
This mode may also cause the inaccuracy as the shapes are presumed.
Figure 140
<< Items to be set for CirEdge detection >>
Shape Type Circle end detection
Surface type Selects from Reflect / Non reflect
Algorithm Type Normal
Mark Threshold
Sets the binarization level.
(When 0 is specified, binarization level is set automatically.
Tolerance
This is used when checking the surface area and perimeter (of the
outer edge of the line detection results). It is also used to check
shape constants.
Search Area Sets the detection range.
Cut Inner Noise Selects from 0 through 9.
Cut Outer Noise Selects from 0 through 9.
Mark Outsize
Sets the Body Size (diameter) of the mark.
(The dimension line in
Figure 140.)
Table 118
3.6. Contour rectangle detection / contour triangle detection
With this recognition method, the linear elements are detected from the contour of the
object with the largest surface area, and from those elements, those that are thought to
be rectangles / triangles are detected and recognized.
As presumed circles are recognized, it is possible to perform recognition in case a part of the
contour is missing.
However, when the missing part of the object is large, it may not be able to be recognized as
the surface area and shape constant are checked before the contour of the circle is presumed.
(Please refer to “3.1.
Center of Gravity detection (Recognition type: Normal)
”.)
“Edge rectangle / triangle detection” should be used for these objects.
This mode may also cause the inaccuracy as the shapes are presumed.
Figure 141