Follow Us

Header Ad

Latest Posts


Artificial intelligence read letters three hundred years ago without opening them

A group of American and European scientists have developed an artificial intelligence algorithm to read unopened letters written 300 years ago.

To decipher the text from the sealed letters, the team scanned the folded documents with X-ray equipment commonly used in dentistry.

Then, artificial intelligence algorithms aligned the scanned images and generated 2D and 3D reconstructions of the letters in both folded and flat state. They also created images of writing surfaces and fold patterns on documents.

“We could have just opened these letters, but instead we took the time to study their hidden, secret and inaccessible qualities,” said Daniel Starsa ​​Smith, professor of early modern English literature at King’s College London.

The letters contain useful information about the past, and the packages themselves are also valuable historical artifacts.

“Our work is aimed at preserving cultural heritage. As soon as a document, such as an unopened letter, is damaged during the opening process, we lose the sense of an intact object, ”the researchers wrote in their paper.

The decrypted documents were securely closed using an archaic process known as letter locking. A sophisticated system of folds and slots allows you to turn a sheet of paper into a separate envelope and protect it from unauthorized access.

One of the documents read with the help of AI was a letter dated July 31, 1697, sent by a lawyer named Jacques Sennac to his cousin Pierre Le Perce, a French merchant living in The Hague.

In it, the sender, with some persistence, asks his cousin for information about the death of another relative and recalls a certain service that he rendered to his cousin in the past.

Sennak’s letter by itself did not reveal radical views of the 17th century. But by analyzing it together with other documents, it could broaden the understanding of the culture, politics and people of early modern Europe.

The researchers say their method may also reveal a number of other historical texts, such as scrolls and books.

As a reminder, in February 2021, MyHeritage introduced an online service using Deep Nostalgia artificial intelligence to create the motion effect of static portrait photography.

Subscribe to ForkLog news on Telegram: ForkLog Feed – the entire news feed, ForkLog – the most important news and polls.

Found a mistake in the text? Select it and press CTRL + ENTER

Fidenge Pecold

My profession is a journalist, but my hobby for 8 years has been studying Forex investing and trading. During this time, I managed to gain extensive experience in investing and trading cryptocurrencies and double my capital in the Forex market. To be the author of this magazine, the site owners invited me to participate in one of the 2020 trading webinars, and I will try to reveal the most relevant crypto market news for you.

    Leave Your Comment

    Your email address will not be published.*

    Forgot Password