Back to Aurora Vision Library website

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


Header: AVL.h
Namespace: avl
Module: MetrologyPro

Performs a series of 1D edge detections and creates a path from the detected points.

Applications: Tracing of an object contour, whose rough location and shape is known beforehand.


void avl::FitPathToEdges
	const avl::Image& inImage,
	const PathFittingMap& inFittingMap,
	const EdgeScanParams& inEdgeScanParams,
	avl::Selection::Type inEdgeSelection,
	atl::Optional<const avl::LocalBlindness&> inLocalBlindness,
	atl::Optional<int> inMaxInterpolationLength,
	atl::Optional<float> inMaxDeviationDelta,
	float inMaxIncompleteness,
	atl::Conditional<avl::Path>& outPath,
	atl::Optional<atl::Array<atl::Conditional<avl::Edge1D>>&> outEdges = atl::NIL,
	atl::Optional<atl::Conditional<avl::Profile>&> outDeviationProfile = atl::NIL,
	atl::Optional<atl::Array<avl::Profile>&> outBrightnessProfiles = atl::NIL,
	atl::Optional<atl::Array<avl::Profile>&> outResponseProfiles = atl::NIL


Name Type Range Default Description
Input value
inImage const Image& Image to fit the path to
Input value
inFittingMap const PathFittingMap& Input fitting map
Input value
inEdgeScanParams const EdgeScanParams& Parameters controlling the edge extraction process
Input value
inEdgeSelection Selection::Type Selection::​Best Selection mode of edges
Input value
inLocalBlindness Optional<const LocalBlindness&> NIL Defines conditions in which weaker edges can be detected in the vicinity of stronger edges
Input value
inMaxInterpolationLength Optional<int> 0 - NIL Maximal number of consecutive points not found
Input value
inMaxDeviationDelta Optional<float> 0.0 - NIL Maximal difference between deviations of consecutive path points
Input value
inMaxIncompleteness float 0.0 - 0.999 0.1f Maximal fraction of edge points not found
Output value
outPath Conditional<Path>& Fitted path or nothing if the fitting failed
Output value
outEdges Optional<Array<Conditional<Edge1D>>&> NIL Found edges
Output value
outDeviationProfile Optional<Conditional<Profile>&> NIL Profile of distances between the actual path points and the corresponding reference path points
Output value
outBrightnessProfiles Optional<Array<Profile>&> NIL Extracted image profiles
Output value
outResponseProfiles Optional<Array<Profile>&> NIL Profiles of the edge (derivative) operator response

Optional Outputs

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

Read more about Optional Outputs.


The operation tries to fit a given path to edges present in the inImage image. Internally, it performs a series of scans with the ScanSingleEdge filter using inFittingMap previously generated from the object being fitted. The found points are then used to determine the actual position of the path in the image. Only inMaxIncompleteness fraction of these scans may fail. If the fitting according to the given parameters is not possible, outPath is set to Nil.

There are also another parameters that control the path fitting process. The inMaxDeviationDelta parameter defines the maximal allowed difference between deviations of consecutive points from the input path points. If some of the scans fail or if some of found points are classified to be wrong according to another control parameters, output path points corresponding to them are interpolated depending on points in their nearest vicinity. No more than inMaxInterpolationLength consecutive points can be interpolated. The exception to this behavior are points which were not found on both ends of the input path. Those are not part of the result at all.


  • Connect an input image to the inImage input.
  • Define inEdgeScanParams.EdgeTransition to detect a particular edge type, and only that type.
  • If no or too few edge points are found, try decreasing inEdgeScanParams.MinMagnitude.
  • If some of the scans may fail, set the inMaxIncompleteness input accordingly.
  • Use the outEdges outputs to visualize the scanning results.


Fitting a path to the edges of a plastic capsule
(inEdgeSelection = First, inEdgeScanParams.EdgeTransition = BrightToDark).


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

  • CreatePathFittingMap – Precomputes a data object that is required for fast path fitting on images.
  • FitPathToRidges – Performs a series of 1D ridge detections and creates a path from the detected points.
  • FitPathToStripe – Performs a series of 1D stripe detections and creates a path from the detected points.
  • FitPathToEdges_Direct – Performs a series of 1D edge detections and creates a path from the detected points.