Back to Aurora Vision Library website

You are here: Start » Function Reference » Computer Vision » Shape Fitting » FitCircleToRidges_Direct

FitCircleToRidges_Direct


Header: AVL.h
Namespace: avl
Module: MetrologyPro

Performs a series of 1D ridge detections and finds a circle that best matches the detected points.

Applications: Precise detection of a thin circular line, whose rough location is known beforehand.

Syntax

C++
C#
 
void avl::FitCircleToRidges_Direct
(
	const avl::Image& inImage,
	const avl::CircleFittingField& inFittingField,
	atl::Optional<const avl::CoordinateSystem2D&> inFittingFieldAlignment,
	int inScanCount,
	int inScanWidth,
	const avl::SamplingParams& inSamplingParams,
	const avl::RidgeScanParams& inRidgeScanParams,
	avl::Selection::Type inRidgeSelection,
	atl::Optional<const avl::LocalBlindness&> inLocalBlindness,
	float inMaxIncompleteness,
	avl::CircleFittingMethod::Type inFittingMethod,
	atl::Optional<avl::MEstimator::Type> inOutlierSuppression,
	atl::Conditional<avl::Circle2D>& outCircle,
	atl::Optional<atl::Array<atl::Conditional<avl::Ridge1D>>&> outRidges = atl::NIL,
	atl::Optional<atl::Conditional<avl::Profile>&> outDeviationProfile = atl::NIL,
	atl::Optional<avl::CircleFittingField&> outAlignedFittingField = atl::NIL,
	atl::Optional<atl::Array<avl::Point2D>&> outInliers = atl::NIL,
	atl::Optional<atl::Array<avl::Profile>&> outBrightnessProfiles = atl::NIL,
	atl::Optional<atl::Array<avl::Profile>&> outResponseProfiles = atl::NIL,
	atl::Array<avl::Segment2D>& diagScanSegments,
	atl::Array<avl::Rectangle2D>& diagSamplingAreas
)

Parameters

Name Type Range Default Description
Input value inImage const Image& Image to fit the circle to
Input value inFittingField const CircleFittingField& Circle fitting field
Input value inFittingFieldAlignment Optional<const CoordinateSystem2D&> NIL Adjusts the fitting field to the position of the inspected object
Input value inScanCount int 3 - 10 The number of points that will be searched to estimate the position of the circle
Input value inScanWidth int 1 - 5 The width of each scan field (in pixels)
Input value inSamplingParams const SamplingParams& Parameters controlling the sampling process
Input value inRidgeScanParams const RidgeScanParams& RidgeScanParams ( ProfileInterpolation: Quadratic4 SmoothingStdDev: 1.0f RidgeWidth: 5 RidgeMargin: 2 MinMagnitude: 5.0f RidgePolarity: Dark ) Parameters controlling the ridge extraction process
Input value inRidgeSelection Selection::Type Selection mode of ridges
Input value inLocalBlindness Optional<const LocalBlindness&> NIL Defines conditions in which weaker ridges can be detected in the vicinity of stronger ridges
Input value inMaxIncompleteness float 0.0 - 0.999 0.1f Maximal fraction of ridge points not found
Input value inFittingMethod CircleFittingMethod::Type AlgebraicTaubin Method used to fit a circle
Input value inOutlierSuppression Optional<MEstimator::Type> NIL Selects a method for ignoring incorrectly detected points
Output value outCircle Conditional<Circle2D>& Fitted circle or nothing if the fitting fails
Output value outRidges Optional<Array<Conditional<Ridge1D>>&> NIL Found ridges
Output value outDeviationProfile Optional<Conditional<Profile>&> NIL Profile of distances between the actual circle points and the corresponding reference circle points
Output value outAlignedFittingField Optional<CircleFittingField&> NIL Fitting field used; in the image coordinate system
Output value outInliers Optional<Array<Point2D>&> NIL Points matching the fitting Circle
Output value outBrightnessProfiles Optional<Array<Profile>&> NIL Extracted image profiles
Output value outResponseProfiles Optional<Array<Profile>&> NIL Profiles of the ridge operator response
Diagnostic input diagScanSegments Array<Segment2D>& Segments along which the scans were run
Diagnostic input diagSamplingAreas Array<Rectangle2D>& Areas from which the input image is sampled

Optional Outputs

The computation of following outputs can be switched off by passing value atl::NIL to these parameters: outRidges, outDeviationProfile, outAlignedFittingField, outInliers, outBrightnessProfiles, outResponseProfiles.

Read more about Optional Outputs.

Description

The operation tries to fit a given circle to ridges present in the inImage image. Internally, it performs a series of scans with the ScanSingleRidge_Direct filter along inScanCount specific scan segments which length is always equal to the inFittingField width and cannot be less than 4. The found points are then used to determine the actual position of the circle in the image. Only inMaxIncompleteness fraction of these scans may fail. If the fitting according to the given parameters is not possible, outCircle is set to Nil.

Hints

  • Connect an input image to the inImage input.
  • Define inRidgeScanParams.RidgePolarity to detect a particular ridge type, and only that type.
  • Adjust inRidgeScanParams.RidgeWidth to the expected thickness of the ridge (in pixels).
  • If no or too few ridge points are found, try decreasing inRidgeScanParams.MinMagnitude.
  • If some of the scans may fail, set the inMaxIncompleteness input accordingly.
  • If some of the scans may produce false results, try different values of the inOutlierSuppression input.
  • Use the outRidges outputs to visualize the scanning results.

Examples

Fitting a circle to a wall of a plastic capsule
(inRidgeScanParams.Polarity = Dark, inRidgeScanParams.RidgeWidth = 3).

Remarks

Read more about Local Coordinate Systems in Machine Vision Guide: Local Coordinate Systems.

This filter is a part of the Shape Fitting toolset. To read more about this technique, one can refer to the Shape Fitting chapter of our Machine Vision Guide

Hardware Acceleration

This operation supports automatic parallelization for multicore and multiprocessor systems.

See Also

  • FitCircleToEdges_Direct – Performs a series of 1D edge detections and finds a circle that best matches the detected points.
  • FitCircleToStripe_Direct – Performs a series 1D stripe detections and finds a circle that best matches the detected points.
  • FitCircleToRidges – Performs a series of 1D ridge detections and finds a circle that best matches the detected points.