David Young

This edge detection looks excellent! It would definitely be a great addition as another edge detection approach, especially for 2D cases. Would you be interested in opening a PR with...

> Sure I always try to work on improvements, but I have no idea how to do this and I don't think I find time to try this out. My...

Great solution! Thanks for sharing it, and glad it has the double benefit of running faster in addition to retaining all labels. We could certainly incorporate this as an edge...

Which label gets lost? If it's a small or unusually shaped label, it may be escaping the contour detection. You could try adjusting parameters for any labels that would be...

That's awesome you solved it! Yeah makes sense that `CHAIN_APPROX_SIMPLE` may have been unable to capture all the turning points for that label, while `CHAIN_APPROX_NONE` kept the full contour and...

> Edge Detection for the AtlasVolume That does look strange. I wonder if it's because the images look relatively blurry as-is, so the gaussian may over-blur them and give no...

> Yes its about the arrow regions, but we thought it came from the "large gaps between the regions" or "ambiguous" definitions for some voxels. I also see those blocks...

Thanks for asking about this, @boazmohar! I get this error as well when I test the groupwise reg. Looks like it's related to this issue (https://github.com/SuperElastix/SimpleElastix/issues/468), where more recent versions...

Thanks for sharing, will definitely consider this. I have not used ANTs extensively, and my understanding is that it can be very accurate but more computationally expensive (see https://ieeexplore.ieee.org/document/8512403). Have...

Thanks for pointing out that wrapper! It looks like a great way to implement ANTs here, and happy to add it as a dependency. I've been using SimpleITK here mainly...