| Operators |
lines_color — Detect color lines and their width.
lines_color(Image : Lines : Sigma, Low, High, ExtractWidth, CompleteJunctions : )
lines_color extracts color lines from the input image Image and returns the extracted lines as subpixel precise XLD-contours in Lines. Color lines are defined as dark lines in the amplitude image of the color edge filter (see edges_color). lines_color always uses the Canny color edge filter. Hence, the required partial derivatives of the image are always computed by convolution with the respective partial derivatives of the Gaussian smoothing masks (see derivate_gauss). The corresponding smoothing is determined by the parameter Sigma.
By defining color lines as dark lines in the amplitude image, in contrast to lines_gauss, for single-channel images no distinction is made whether the lines are darker or brighter than their surroundings. Furthermore, lines_color also returns staircase lines, i.e., lines for which the gray value of the lines lies between the gray values in the surrounding area to the left and right sides of the line. In multi-channel images, the above definition allows each channel to have a different line type. For example, in a three-channel image the first channel may have a dark line, the second channel a bright line, and the third channel a staircase line at the same position.
If ExtractWidth is set to 'true' the line width is extracted for each line point. Because the line extractor is unable to extract certain junctions because of differential geometric reasons, it tries to extract these by different means if CompleteJunctions is set to 'true'.
lines_color links the line points into lines by using an algorithm similar to a hysteresis threshold operation, which is also used in lines_gauss and edges_color_sub_pix. Points with an amplitude larger than High are immediately accepted as belonging to a line, while points with an amplitude smaller than Low are rejected. All other points are accepted as lines if they are connected to accepted line points (see also lines_gauss). Here, amplitude means the line amplitude of the dark line (see lines_gauss and lines_facet). This value corresponds to the third directional derivative of the smoothed input image in the direction perpendicular to the line.
For the choice of the thresholds High and Low one has to keep in mind that the third directional derivative depends on the amplitude and width of the line as well as the choice of Sigma. The value of the third derivative depends linearly on the amplitude, i.e., the larger the amplitude, the larger the response. For the width of the line there is an inverse dependence: The wider the line is, the smaller the response gets. This holds analogously for the dependence on Sigma: The larger Sigma is chosen, the smaller the second derivative will be. This means that for larger smoothing correspondingly smaller values for High and Low should be chosen.
The extracted lines are returned in a topologically sound data structure in Lines. This means that lines are correctly split at junction points.
lines_color defines the following attributes for each line point if ExtractWidth was set to 'false':
The angle of the direction perpendicular to the line (oriented such that the normal vectors point to the right side of the line as the line is traversed from start to end point; the angles are given with respect to the row axis of the image.)
The magnitude of the second derivative
If ExtractWidth was set to 'true', additionally the following attributes are defined:
The line width to the left of the line
The line width to the right of the line
All these attributes can be queried via the operator get_contour_attrib_xld.
In general, but in particular if the line width is to be extracted, should be selected, where w is the width (half the diameter) of the lines in the image. As the lowest allowable value must be selected. If, for example, lines with a width of 4 pixels (diameter 8 pixels) are to be extracted, should be selected. If it is expected that staircase lines are present in at least one channel, and if such lines should be extracted, in addition to the above restriction, should be selected. This is necessary because staircase lines turn into normal step edges for large amounts of smoothing, and therefore no longer appear as dark lines in the amplitude image of the color edge filter.
Note that filter operators may return unexpected results if an image with a reduced domain is used as input. Please refer to the chapter Filters.
Input image.
Extracted lines.
Amount of Gaussian smoothing to be applied.
Default value: 1.5
Suggested values: 1, 1.2, 1.5, 1.8, 2, 2.5, 3, 4, 5
Typical range of values: 0.7 ≤ Sigma ≤ 20
Recommended increment: 0.1
Lower threshold for the hysteresis threshold operation.
Default value: 3
Suggested values: 0, 0.5, 1, 2, 3, 4, 5, 8, 10
Typical range of values: 0 ≤ Low
Recommended increment: 0.5
Restriction: Low >= 0
Upper threshold for the hysteresis threshold operation.
Default value: 8
Suggested values: 0, 0.5, 1, 2, 3, 4, 5, 8, 10, 12, 15, 18, 20, 25
Typical range of values: 0 ≤ High
Recommended increment: 0.5
Restriction: High >= 0 && High >= Low
Should the line width be extracted?
Default value: 'true'
List of values: 'false', 'true'
Should junctions be added where they cannot be extracted?
Default value: 'true'
List of values: 'false', 'true'
The amount of temporary memory required is dependent on the height H of the domain of Image.
lines_color returns 2 (H_MSG_TRUE) if all parameters are correct and no error occurs during execution. If the input is empty the behavior can be set via set_system(::'no_object_result',<Result>:). If necessary, an exception is raised.
edges_color, edges_color_sub_pix
C. Steger: “Subpixel-Precise Extraction of Lines and Edges”;
International Archives of Photogrammetry and Remote Sensing,
vol. XXXIII, part B3; pp. 141-156; 2000.
C. Steger: “An Unbiased Detector of Curvilinear Structures”; IEEE
Transactions on Pattern Analysis and Machine Intelligence; vol. 20,
no. 2; pp. 113-125; 1998.
C. Steger: “Unbiased Extraction of Curvilinear Structures from 2D
and 3D Images”; Herbert Utz Verlag, München; 1998.
2D Metrology
| Operators |