fuzzy_measure_pairs ( Image : : MeasureHandle, Sigma, AmpThresh, FuzzyThresh, Transition : RowEdgeFirst, ColumnEdgeFirst, AmplitudeFirst, RowEdgeSecond, ColumnEdgeSecond, AmplitudeSecond, RowEdgeCenter, ColumnEdgeCenter, FuzzyScore, IntraDistance, InterDistance )

Extract straight edge pairs perpendicular to a rectangle or an annular arc.

fuzzy_measure_pairs serves to extract straight edge pairs which lie perpendicular to the major axis of a rectangle or an annular arc. In addition to measure_pairs it uses fuzzy member functions to evaluate and select the edge pairs.

The extraction algorithm is identical to fuzzy_measure_pos. In addition, the edges are grouped to pairs: If Transition = 'positive', the edge points with a dark-to-light transition in the direction of the major axis of the rectangle or annular arc are returned in RowEdgeFirst and ColumnEdgeFirst. In this case, the corresponding edges with a light-to-dark transition are returned in RowEdgeSecond and ColumnEdgeSecond. If Transition = 'negative', the behavior is exactly opposite. If Transition = 'all', the first detected edge defines the transition for RowEdgeFirst and ColumnEdgeFirst.

Having extracted subpixel edge locations, the edges are paired. The pairing algorithm groups the edges such that interleavings and inclusions of pairs are prohibited. The features of an edge pair are evaluated by a fuzzy function, which can be set by set_fuzzy_measure or set_fuzzy_measure_norm_pair. Which edge pairs are selected can be determined with the parameter FuzzyThresh, which constitutes a threshold on the weight over all fuzzy sets, i.e., the geometric mean of the weights of the defined fuzzy member functions.

The selected edges are returned as single points, which lie on the major axis of the rectangle or annular arc. The corresponding edge amplitudes are returned in AmplitudeFirst and AmplitudeSecond, the fuzzy scores in FuzzyScore. In addition, the distance between each edge pair is returned in IntraDistance and the distance between consecutive edge pairs is returned in InterDistance. Here, IntraDistance[i] corresponds to the distance between EdgeFirst[i] and EdgeSecond[i], while InterDistance[i] corresponds to the distance between EdgeSecond[i] and EdgeFirst[i+1], i.e., the tuple InterDistance contains one element less than the tuples of the edge pairs.


Attention

fuzzy_measure_pairs only returns meaningful results if the assumptions that the edges are straight and perpendicular to the major axis of the rectangle or annular arc are fulfilled. Thus, it should not be used to extract edges from curved objects, for example. Furthermore, the user should ensure that the rectangle or a annular arc is as close to perpendicular as possible to the edges in the image.

It should be kept in mind that fuzzy_measure_pairs ignores the domain of Image for efficiency reasons. If certain regions in the image should be excluded from the measurement a new measure object with appropriately modified parameters should be generated.


Parameters

Image (input_object)
singlechannelimage -> object : byte / uint2
Input image.

MeasureHandle (input_control)
measure_id -> integer
Measure object handle.

Sigma (input_control)
number -> real
Sigma of Gaussian smoothing.
Default value: 1.0
Suggested values: 0.4, 0.6, 0.8, 1.0, 1.5, 2.0, 3.0, 4.0, 5.0, 7.0, 10.0
Typical range of values: 0.4 <= Sigma <= 100 (lin)
Minimum increment: 0.01
Recommended increment: 0.1
Restriction: Sigma >= 0.4

AmpThresh (input_control)
number -> real
Minimum edge amplitude.
Default value: 30.0
Suggested values: 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 90.0, 110.0
Typical range of values: 1 <= AmpThresh <= 255 (lin)
Minimum increment: 0.5
Recommended increment: 2

FuzzyThresh (input_control)
number -> real
Minimum fuzzy value.
Default value: 0.5
Suggested values: 0.1, 0.3, 0.5, 0.7, 0.9
Typical range of values: 0.0 <= FuzzyThresh <= 1.0 (lin)
Recommended increment: 0.1

Transition (input_control)
string -> string
Select the first gray value transition of the edge pairs.
Default value: 'all'
List of values: 'all', 'positive', 'negative'

RowEdgeFirst (output_control)
point.y-array -> real
Row coordinate of the first edge point.

ColumnEdgeFirst (output_control)
point.x-array -> real
Column coordinate of the first edge point.

AmplitudeFirst (output_control)
real-array -> real
Edge amplitude of the first edge (with sign).

RowEdgeSecond (output_control)
point.y-array -> real
Row coordinate of the second edge point.

ColumnEdgeSecond (output_control)
point.x-array -> real
Column coordinate of the second edge point.

AmplitudeSecond (output_control)
real-array -> real
Edge amplitude of the second edge (with sign).

RowEdgeCenter (output_control)
point.y-array -> real
Row coordinate of the center of the edge pair.

ColumnEdgeCenter (output_control)
point.x-array -> real
Column coordinate of the center of the edge pair.

FuzzyScore (output_control)
real-array -> real
Fuzzy evaluation of the edge pair.

IntraDistance (output_control)
real-array -> real
Distance between edges of an edge pair.

InterDistance (output_control)
real-array -> real
Distance between consecutive edge pairs.


Result

If the parameter values are correct the operator fuzzy_measure_pairs returns the value 2 (H_MSG_TRUE). Otherwise an exception handling is raised.


Parallelization Information

fuzzy_measure_pairs is reentrant and processed without parallelization.


Possible Predecessors

gen_measure_rectangle2, gen_measure_arc, set_fuzzy_measure


Possible Successors

close_measure


Alternatives

edges_sub_pix, fuzzy_measure_pairing, measure_pairs


See also

fuzzy_measure_pos, measure_pos


Module

Sub-pixel operators



Copyright © 1996-2005 MVTec Software GmbH