What is the use of minRepeatability parameter of SimpleBlobDetector in OpenCV?

Question

There is a minRepeatability parameter in SimpleBlobDetector in OpenCV. What is the use of this parameter. How will it affect blob detection if I va

Answer 1

The relevant code is in blobdetector.cpp.

The detect function (the only one using minRepeatability):

1. finds blob centers at different threshold (from minThreshold to maxThreshold with thresholdStep) on the grayscale image
2. if the same blob center is found at different threshold values (within a minDistBetweenBlobs), then it (basically) increases a counter for that blob.
3. if the counter for each blob is >= minRepeatability, then it's a stable blob, and produces a KeyPoint, otherwise the blob is discarded.

So minRepeatability is how a blob is stable across different thresholds on the grayscale image.

Default values are:

thresholdStep = 10;
minThreshold = 50;
maxThreshold = 220;
minRepeatability = 2;
minDistBetweenBlobs = 10;

The max valid value for minRepeatability is then: (maxThreshold - minThreshold) / thresholdStep, or every blob will be discarded. The minimum valid value is 1, meaning that all blobs will be kept and provide a KeyPoint.