17-12-2024, 06:49 PM
Thank you!
With this version of the model I think it's impossible to uncover anything that wasn't already known from inspecting the color TIFFs or the original manuscript.
In principle there is a small chance that with some creative design of the training process it will be possible to produce a model that could exploit statistical variations to detect ink where no amount of standard color correction can bring it out.
Regarding the images you posted, I can't see any particular letter shapes there, can you?
With this version of the model I think it's impossible to uncover anything that wasn't already known from inspecting the color TIFFs or the original manuscript.
In principle there is a small chance that with some creative design of the training process it will be possible to produce a model that could exploit statistical variations to detect ink where no amount of standard color correction can bring it out.
Regarding the images you posted, I can't see any particular letter shapes there, can you?