You are here: Start » Function Reference » Computer Vision » Hough Transform » DetectSegments

DetectSegments

Header:	FIL.h
Namespace:	fil
Module:	FoundationBasic

Finds segments in an image using Hough Transform.

Syntax

void fil::DetectSegments
(
	const fil::Image& inImage,
	ftl::Optional<const fil::Region&> inRoi,
	float inAngleResolution,
	float inMinAngleDelta,
	float inMinDistance,
	float inMinLength,
	float inMinScore,
	float inEdgeThreshold,
	ftl::Array<fil::Segment2D>& outSegments,
	fil::Image& diagGradientMagnitudeImage,
	fil::Image& diagScoreImage
)

Parameters

Name	Type	Range	Default	Description
inImage	const Image&			Input image
inRoi	Optional<const Region&>		NIL	Input region of interest
inAngleResolution	float	0.1 - 180.0	1.0f	Resolution of segments' orientation
inMinAngleDelta	float	0.0 -	20.0f	Minimum angle between two segments
inMinDistance	float	0.0 -	20.0f	Minimum distance between two segments
inMinLength	float	0.0 -	20.0f	Minimum segment length
inMinScore	float	0.0 -	20.0f	Minimum matching score
inEdgeThreshold	float		10.0f	Minimum accepted edge magnitude
outSegments	Array<Segment2D>&			Output segments
diagGradientMagnitudeImage	Image&			Visualized gradients magnitude of an input image
diagScoreImage	Image&			Calculated score for each pixel of an input image

Description

The operation detects straight edges in the inImage using the Hough Transform approach and treats them as segments by tracing gradients along lines. The output array is ordered from best matching to worst matching results.

The parameter inAngleResolution specifies the precision of detected lines' orientations. Value of n means the filter will be able to reliably distinguish lines in n-degree increments.

Parameters inMinAngleDelta and inMinDistance are used for neighbouring results suppression. inMinAngleDelta specifies the minimum angle between two lines while inMinDistance specifies the minimum distance between two parallel lines. Parameter inMinLength limits the length of segments (in pixels), suppressing too short segments.

The orientations of the resulting segments are always between 0 and 180 degrees.

Examples

DetectSegments performed on the sample image with inMinScore = 0.5, inMinLength = 25.

Remarks