Circle Detection

Overview

Circle Detection node finds circular regions in an input frame using the Hough circle transform and returns the center coordinates and radius of each detected circle.

Use this node to locate circular objects such as bottle caps, coins, holes, lenses, or pipe openings in industrial inspection, quality control, or measurement flows.

Input

Input Image

image required

The image frame to analyze. Connect this to a camera or upstream processing output.

Blur Size

integer required

Gaussian blur kernel size applied before circle detection. Blurring reduces noise and helps avoid spurious circle detections from texture or fine detail.

Values: 1, 3, 5, 7, 9
Default: 3

Higher values apply stronger smoothing. Use 1 to disable blurring.

Accumulator Resolution

number required

Ratio of the Hough accumulator resolution to the image resolution. A value of 1 uses the same resolution as the input image; 2 uses half the resolution.

Range: 1.0 to 2.0
Default: 1.0

Higher values reduce memory use and speed up detection at the cost of less precise circle localization.

Minimum Distance

integer required

Minimum distance in pixels between the centers of two detected circles. Circles closer than this distance are merged into one.

Range: 0 to 9999
Default: 10

Increase this value when circles in your scene should not overlap, to avoid duplicate detections.

Canny Edge Threshold

integer required

Higher threshold of the two thresholds passed to the internal Canny edge detector (the lower threshold is set automatically to half this value). Controls how strongly defined an edge must be before it is considered when voting for a circle.

Range: 0 to 500
Default: 100

Higher values require more prominent edges, reducing false positives in noisy images.

Accumulator Threshold

integer required

Minimum number of votes a circle center must receive in the Hough accumulator to be accepted as a detection. Higher values require more evidence for each circle.

Range: 0 to 500
Default: 50

Increase this to reduce false positives; decrease it to detect weaker or partial circles.

Detectable Circle Radius Range

array required

Minimum and maximum circle radius in pixels. Circles outside this range are discarded.

• Min Radius — default: 10
• Max Radius — default: 100

Set this range to match the expected size of circles in your frame to avoid detecting irrelevant circular patterns.

Overlay Results

boolean required

Whether to draw detected circle outlines and center points on the output frame. See Overlay Results.

Output

Overlay Image

image

Output frame from the node. If overlays are enabled, detected circles are drawn with their outlines and center markers.

Detected Count

integer

Number of circles detected in the current frame.

Detected Circles

array

Array of circle detection objects. Each object contains:

• circle array: A three-element array [x, y, radius] where x and y are the pixel coordinates of the center and radius is the circle radius in pixels.