Experts said that there is a huge amount of material and manuscripts that have survived to our
Researchers at the University of Notre Dame are now developing AI to read complex ancient handwriting in order to improve its transcription.
We decided to automate the transcription in such a way that it simulates how an experienced reader perceives the text.
Walter Schairer, Assistant Professor, Dennis O. Doughty College
In the new work, its authors combined traditionalMachine learning techniques with visual psychophysics are a method of measuring connections between physical stimuli and mental phenomena, such as the amount of time it takes a skilled reader to recognize a particular character, the quality of handwriting, or determine how an abbreviation is spelled.
Schairer's team studied digitized Latinmanuscripts that were written in the monastery of St. Gall in the 9th century. Readers entered transcriptions into a specially designed software interface. The team then measured reaction times during transcription to understand which words, symbols and passages were easy and which were difficult. Scheirer explained that this is necessary to get closer to the human perception of the text, this will reduce the number of errors and the AI will decipher the text more accurately.
Now the team is working on increasingaccuracy of transcriptions, especially when working with damaged or incomplete documents, and how to interpret images and other associated symbols that can lead to confusion.
Read more
See how a black hole begins to destroy a star
New particle discovered at the Large Hadron Collider
NASA: the situation with the module "Science" is more serious than previously announced