segment_characters — Segments characters in a given region of an image.
segment_characters(Region, Image : ImageForeground, RegionForeground : Method, EliminateLines, DotPrint, StrokeWidth, CharWidth, CharHeight, ThresholdOffset, Contrast : UsedThreshold)
This operator is used to segment characters in a given Region of an
Image. The Region is only used to reduce the working area.
The segmented characters are returned in RegionForeground.
Two different methods to detect the characters are supplied.
All segmentation methods assume that the text ist darker than the
background. If this is not the case, please invert the image with
invert_image.
The parameter Method determines the algorithm for text
segmentation. The possible values are
This method extracts text that differ locally from the
background. Therefore, it is suited for images with
inhomogeneous illumination. The enhancement of the text
borders, leads to a more accurate determination of the
outline of the text. Which is especially useful if the
background is highly textured. The parameter
Contrast defines the minimum contrast,i.e.,
the minimum gray value difference between symbols and
background.
The minimum contrast is estimated automatically such
that the number of very small regions is reduced. This
method is especially suitable for noisy images. The
parameter ThresholdOffset can be used to adjust
the threshold.
Let g(x,y) be the gray value at position (x,y) in the
input Image. The threshold condition is
determined by:
.
Select EliminateLines if the extraction of characters is disturbed
by lines that are horizontal or vertical with respect to the lines of
text and set its value to 'true'. The elimination is influenced by the
maximum of CharWidth and the maximum of CharHeight.
For further information see the description of these parameters.
DotPrint:
Should be set to 'true' if dot prints should be read, else to 'false'.
StrokeWidth:
Specifies the stroke width of the text. It is used to calculate internally
used mask sizes to determine the characters. This mask sizes are also
influenced through the parameters DotPrint, the average
CharWidth, and the average CharHeight.
CharWidth:
This can be a tuple with up to three values. The first value is the
average width of a character. The second is the minimum width of a
character and the third is the maximum width of a character.
If the minimum is not set or equal -1, the operator automatically sets
these value depending on the average CharWidth. The same is
the case if the maximum is not set. Some examples:
[10] sets the average character width to 10, the minimum and maximum are calculated by the operator.
[10,-1,20] sets the average character width to 10, the minimum value is calculated by the system, and the maximum is set to 20.
[10,5,20] sets the average character width to 10, the minimum to 5, and the maximum to 20.
CharHeight:
This can be a tuple with up to three values. The first value is the
average height of a character. The second is the minimum height of a
character and the third is the maximum height of a character.
If the minimum is not set or equal -1, the operator automatically sets
these value depending on the average CharHeight. The same is
the case if the maximum is not set. Some examples:
[10] sets the average character height to 10, the minimum and maximum are calculated by the operator.
[10,-1,20] sets the average character height to 10, the minimum value is calculated by the system, and the maximum is set to 20.
[10,5,20] this sets the average character height to 10, the minimum to 5, and the maximum to 20.
ThresholdOffset:
This parameter can be used to adjust the threshold, which is used when the
segmentation method 'local_auto_shape' is chosen.
Contrast:
Defines the minimum contrast between the text and the background. This
parameter is used if the segmentation method 'local_contrast_best'
is selected.
UsedThreshold:
After the execution, this parameter returns the threshold used to
segment the characters.
ImageForeground returns the image that was internally used for the
segmentation.
Region (input_object) region(-array) → object
Area in the image where the text lines are located.
Image (input_object) singlechannelimage → object (byte / uint2)
Input image.
ImageForeground (output_object) image(-array) → object (byte / uint2)
Image used for the segmentation.
RegionForeground (output_object) singlechannelregion(-array) → object
Region of characters.
Method (input_control) string → (string)
Method to segment the characters.
Default value: 'local_auto_shape'
List of values: 'local_auto_shape', 'local_contrast_best'
EliminateLines (input_control) string → (string)
Eliminate horizontal and vertical lines?
Default value: 'false'
List of values: 'false', 'true'
DotPrint (input_control) string → (string)
Should dot print characters be detected?
Default value: 'false'
List of values: 'false', 'true'
StrokeWidth (input_control) string → (string)
Stroke width of a character.
Default value: 'medium'
List of values: 'bold', 'light', 'medium', 'ultra_light'
CharWidth (input_control) integer-array → (integer)
Width of a character.
Default value: 25
Typical range of values: 1
≤
CharWidth
Restriction: CharWidth >= 1
CharHeight (input_control) integer-array → (integer)
Height of a character.
Default value: 25
Typical range of values: 1
≤
CharHeight
Restriction: CharHeight >= 1
ThresholdOffset (input_control) integer → (integer)
Value to adjust the segmentation.
Default value: 0
Contrast (input_control) integer → (integer)
Minimum gray value difference between text and background.
Default value: 10
Typical range of values: 1
≤
Contrast
Restriction: Contrast >= 1
UsedThreshold (output_control) integer(-array) → (integer)
Threshold used to segment the characters.
for Index := 1 to 5 by 1
read_image (Image, 'dot_print_rotated/dot_print_rotated_'+Index$'02d')
text_line_orientation (Image, Image, 50, rad(-30), rad(30), OrientationAngle)
rotate_image (Image, ImageRotate, deg(-OrientationAngle), 'constant')
segment_characters (ImageRotate, ImageRotate, ImageForeground, \
RegionForeground, 'local_auto_shape', 'false', 'false', 'medium', \
25, 25, 0, 10, UsedThreshold)
endfor
If the input parameters are set correctly, the operator
segment_characters returns the value 2 (H_MSG_TRUE). Otherwise an
exception will be raised.
Foundation