edge threshold

[michath]

seems the local threshold in the paper is implemented as global (=13) in tools/segmentation.py:
does it indeed? if so, how much effort is required to make it locally adaptive?
thanks!

[MichalBusta]

Hi,
so far we have tested several variants:

• threshold t as function of intensity of the central pixel (see #ifdef RELATIVE_THRESH in FASTex.cpp)
• otsu-like estimate

for ICDAR dataset, the ROC curve does not improve much (but it can be profitable for specific task)

do you have suggestion?

[michath]

only that threshold optimization should probably account for overlapping between correct and incorrect text regions: precision matters more while overlapping whereas recall matters more while there is no overlapping.