Scientists from the Russian company Smart Engines and the Federal Research Center "Informatics and Management" (FRC IU RAS) have taught artificial intelligence (AI) to read information from fragile scrolls and books with the click of a button. This was reported in the press service of Smart Engines.
The developed technology is based on X-ray tomography and machine vision algorithms. The selected document is placed in a tomograph, then a digital copy is created. Information is extracted without physical contact with the data carrier.
The development will allow studying texts of paper, birch bark and silver scrolls and printed books that have suffered from natural aging, exposure to moisture or fires, and are stored in special conditions.
A data corpus containing six samples of documents rolled up in different ways was used to train the AI. They contained letters, numbers and graphic elements of different sizes.
The authors of the idea hope that the development will help open up new opportunities for researchers in the humanities and preserve cultural heritage. In the future, it is planned to find investors to scale the technology.
Earlier www1.ru reported that in St. Petersburg they trained a neural network to identify vulnerabilities in text captchas.
Read materials on the topic:
Reshetnev employees are developing an AI technologist for satellite construction
Russian AI will start making voice comments to scooter riders and smokers
Now on home
Start of deliveries scheduled for 2027
Over 51,000 new motorcycles were sold in Russia in 2025
The car will take at least a year to assemble
The application's audience has reached 20 million users
The model will be included in the list of cars for taxis, price - from 2.25 million rubles
All parking lots of the "Administrator of the Moscow Parking Space" are connected to the service
The cars will be supplied to the Moscow Transport Service Directorate
Deliveries to India may begin in 2028
The technology provides automated search for all types of defects in power units
The plane flew 500 km, accelerating to 425 km/h
The plant stated that the information about the termination of purchases for models 6 and 8 is not true
Scientists are using the "Ekran-M" installation