Building Computer Vision Projects with OpenCV 4 and C++

Extremal regions

Extremal regions are connected areas that are characterized by almost uniform intensity, which is surrounded by a contrasted background. The stability of a region can be measured by calculating how resistant to thresholding variance the region is. This variance can be measured with a simple algorithm:

1. Apply the threshold, generating an image, A. Detect its connected pixels regions (extremal regions).
2. Increase the threshold by a delta amount, generating an image, B. Detect its connected pixels regions (extremal regions).
3. Compare image B with A. If a region in image A is similar to the same region in image B, add it to the same branch in the tree. The criteria of similarity may vary from implementation to implementation, but ...