Lesion on edge of leaves is ignored when segmented.

[YaredTaddese]

Lesion on edge of leaves is ignored when segmented, practically denying that the lesion is part of the leaf and considering it as background rather than leaf part. This results in a bad segmentation for applications that rely on the existence of such lesion parts of leaves in the input, for example, for applications that detect plant diseases and the likes.

[jeffreyhuang823]

Thank's that you have done a great job. In the paper (4.2 Leaf shape refinement), shall it be fixed by fit to the smooth data in a least squares sense?

[Tarcisiofl]

YaredTaddese did you find any solution for it? I have implemented a leaf segmentation using Expectation Maximization. However, sometimes the background is segmented as part of the leaf.