Back to Adaptive Vision Studio website

You are here: Start » Filter Reference » Image Thresholding » ThresholdToRegion_Dynamic


Thresholds an image relatively to the average pixel value in a local rectangular neighborhood.

Name Type Range Description
inImage Image Input image
inRoi Region* Region in which pixels are written
inSourceRoi Region* Region from which pixels are read
inRadiusX Integer 0 - 65535 Horizontal radius of internal mean blur
inRadiusY Integer* 0 - 65535 Vertical radius of internal mean blur (Auto = inRadiusX)
inMinRelativeValue Real* Minimum relative value of a pixel that is considered foreground (Auto = -INF)
inMaxRelativeValue Real* Maximum relative value of a pixel that is considered foreground (Auto = +INF)
inHysteresis Real 0.0 - Defines how much the threshold criteria are lowered for pixels neighboring with other foreground pixels
outRegion Region Output region
diagBaseImage Image Diagnostic blurred image.


Useful in case of uneven illumination.


The operation is a cousin of ThresholdImage_Dynamic yet computes a region instead of an image. The resulting region contains only those pixels of the input image, which are brighter at least by inMinRelativeValue and at most by inMaxRelativeValue than the local average. If any of the parameters inMinRelativeValue, inMaxRelativeValue is not set, it is assumed to be, accordingly, -infinity or infinity.

Pixel neighbourhood used to compute the local average is a rectangle of dimensions (2 \cdot \text{\textbf{inRadiusX} }+1) \times (2 \cdot \text{\textbf{inRadiusY} }+1) centered at the pixel being processed.

In the multichannel images the operation uses an average of channel values in each pixel.


  • Define inMinRelativeValue to extract objects which are brighter than the neighborhood.
  • Define inMaxRelativeValue to extract objects which are darker than the neighborhood.
  • Increase inRadiusX (and optionally inRadiusY) to define a bigger neighborhood.


Description of usage of this filter can be found in examples and tutorial: Capsules, OCR Read Number (MLP), OCR Read Number (SVM), Preparing an OCR model.

ThresholdToRegion_Dynamic performed on the sample image with inMinRelativeValue = 5.0, inMaxRelativeValue = auto.


This filter can throw an exception to report error. Read how to deal with errors in Error Handling.

List of possible exceptions:

Error type Description
DomainError Region exceeds an input image in ThresholdToRegion_Dynamic.
DomainError Roi exceeds image dimensions in ThresholdToRegion_Dynamic.
DomainError Source roi exceeds image dimensions in ThresholdToRegion_Dynamic.

Complexity Level

This filter is available on Basic Complexity Level.

Filter Group

This filter is member of ThresholdToRegion filter group.

See Also

  • ThresholdImage_Dynamic – Thresholds an image relatively to some value calculated in a local rectangular neighbourhood.