You are here: Start » Computer Vision » 2D Edge Detection » DetectEdges

DetectEdges

Extracts a binary image of pixel-precise continuous edges.

Applications: Consistent detection of pixels that belong to contours of variable or unpredictable shape, e.g. screw thread outline or a custom piece of textile.

Syntax

void avl::DetectEdges
(
	const avl::Image& inImage,
	atl::Optional<const avl::Region&> inRoi,
	avl::EdgeFilter::Type inEdgeFilter,
	float inStdDevX,
	atl::Optional<float> inStdDevY,
	float inEdgeThreshold,
	float inEdgeHysteresis,
	float inMaxJoiningDistance,
	const int inMinBlobArea,
	avl::Image& outEdgesImage,
	avl::Image& diagGradientMagnitudeImage
)

Parameters

	Name	Type	Range	Default	Description
	inImage	const Image&			Image from which edges will be extracted
	inRoi	Optional<const Region&>		NIL	Region of the image from which edges will be extracted
	inEdgeFilter	EdgeFilter::Type			Type of edge filter used for computing gradients
	inStdDevX	float	0.0 -	2.0f	Amount of horizontal smoothing used by the edge filter
	inStdDevY	Optional<float>	0.0 -	NIL	Amount of vertical smoothing used by the edge filter (Auto = inStdDevX)
	inEdgeThreshold	float	0.0 -	15.0f	Sufficient edge strength; edges of that strength will always be detected
	inEdgeHysteresis	float	0.0 -	5.0f	Value by which the edge threshold is decreased for edge points neighboring with sufficiently strong edges
	inMaxJoiningDistance	float	0.0 -	0.0f	Maximal distance between edges that can be joined
	inMinBlobArea	const int	0 -	1	Minimal area of an edge blob
	outEdgesImage	Image&			Image of found edges
	diagGradientMagnitudeImage	Image&			Visualization of the gradient magnitude

In-place Processing

This function supports in-place data processing - you can pass the same reference to inImage and outEdgesImage

Read more about In-place Computation.

Hardware Acceleration