Decoding ancient scrolls from Pompeii

This sums up the problem:

The reason is that there were no printing presses in ancient and medieval times, so books had to be copied by hand.  If they weren't copied, the material would decay and the book would be lost.  Books were very expensive, which is why so few survived.

However, the volcanic eruption that buried Pompeii buried an ancient library.  The scrolls blackened from the heat but are intact.  People have been using cat scanning technology to image the insides, and are now trying to apply machine learning to decode what is ink and what is not.  While we can't yet read the scrolls, it seems that some real advancement in technique is being made:

This character is harder to make out, until the reader realizes that it is curved. It is first visible when looking for the dark narrow cracks in the “cracked mud” texture. It is a handwritten lunate sigma, which looks like a ‘c’.  The field of view is 3.35 mm high. The character is aligned directly to the right of the iota and pi characters, consistent in size, orthography, line width, alignment, ink texture, ink position relative to the papyrus, etc. Like the Pi, slight stroke width variations are recognizably derived from the motion of hand writing. 

With three characters (pi, iota, sigma) we can check if this is part of a word – of course it could be two words since ancient writing generally did not include spaces between words. Using this handy list (https://kyle-p-johnson.com/assets/most-common-greek-words.txt) we find 69 instances of πισ, and none of πγσ or πτσ.

This is a long and technical post but it is a really interesting approach to unlocking actual ancient mysteries.