We're finally reading the secrets of Herculaneum's lost library A whole library's worth of papyri owned by Julius Caesar's father-in-law were turned to charcoal by the eruption of Vesuvius. Deep within a particle accelerator, theoretical physicist Giorgio Angelotti is hard at work. He sets a black cylinder on a mount, bolts it down, then runs through some safety checks before retreating from the chamber, known as "the hatch". "You have to be sure there's no one in the hatch before you close the door," he says. That's because he is about to blast the sample with a super-powerful beam of X-rays.

A closed carbonised papyrus scroll from Herculaneum being scanned. The Vesuvius Challenge is an unparalleled competition in the field of classical studies, with the potential to pave the way for something akin to a second Renaissance. Its objective is to use artificial intelligence (AI) to virtually unroll hundreds of closed papyrus scrolls, containing ancient literature that has not been seen for 2,000 years. When Mount Vesuvius erupted in AD79, it buried various cities at the Gulf of Naples under massive volcanic material – including Herculaneum, located near Pompeii. In the 18th century, an exceptionally luxurious Roman villa was excavated there, close to the ancient city walls and shoreline. The villa's marvellous wall paintings, mosaics, busts and statues had been conserved by the ashes.

Reproduced under a CC BY 4.0 license. On 19 October 1752, a discovery was made 20 metres underneath the town of Resina, near Naples in Italy. Peasants digging wells in the area around Mount Vesuvius had struck marble statuary and mosaic pavements – and they also found lumps of carbon. Initially, they were tossed aside – the lumps weren't considered valuable or pretty, so were of no interest. But thankfully, someone noticed they were all about the same size and shape, and investigated further.

Detecting and recognizing characters in Greek papyri with YOLOv8, DeiT and SimCLR Robert Turnbull, Evelyn Mannix First place in character recognition challenge Second place in character detection challenge Best recall and precision results for detection and recognition results for IoU 0.5 Releasing prediction results in multiple formats for 4500+ Oxyrhynchus Papyri images Abstract The capacity to isolate and recognize individual characters from facsimile images of papyrus manuscripts yields rich opportunities for digital analysis. For this reason the'ICDAR 2023 Competition on Detection and Recognition of Greek Letters on Papyri' was held as part of the 17 We used an ensemble of YOLOv8 models to detect and classify individual characters and employed two different approaches for refining the character predictions, including a transformer based DeiT approach and a ResNet-50 model trained on a large corpus of unlabelled data using SimCLR, a self-supervised learning method. Our submission won the recognition challenge with a mAP of 42.2%, and was runner-up in the detection challenge with a mean average precision (mAP) of 51.4%. At the more relaxed intersection over union threshold of 0.5, we achieved the highest mean average precision and mean average recall results for both detection and classification. We ran our prediction pipeline on more than 4,500 images from the Oxyrhynchus Papyri to illustrate the utility of our approach, and we release the results publicly in multiple formats.

We present a complete software pipeline for revealing the hidden texts of the Herculaneum papyri using X-ray CT images. This enhanced virtual unwrapping pipeline combines machine learning with a novel geometric framework linking 3D and 2D images. We also present EduceLab-Scrolls, a comprehensive open dataset representing two decades of research effort on this problem. EduceLab-Scrolls contains a set of volumetric X-ray CT images of both small fragments and intact, rolled scrolls. The dataset also contains 2D image labels that are used in the supervised training of an ink detection model. Labeling is enabled by aligning spectral photography of scroll fragments with X-ray CT images of the same fragments, thus creating a machine-learnable mapping between image spaces and modalities. This alignment permits supervised learning for the detection of "invisible" carbon ink in X-ray CT, a task that is "impossible" even for human expert labelers. To our knowledge, this is the first aligned dataset of its kind and is the largest dataset ever released in the heritage domain. Our method is capable of revealing accurate lines of text on scroll fragments with known ground truth. Revealed text is verified using visual confirmation, quantitative image metrics, and scholarly review. EduceLab-Scrolls has also enabled the discovery, for the first time, of hidden texts from the Herculaneum papyri, which we present here. We anticipate that the EduceLab-Scrolls dataset will generate more textual discovery as research continues.

The Greek word for "purple" has been extracted from a Herculaneum scroll Almost 2000 years after they were buried by the volcanic eruption of Mount Vesuvius in AD 79, scrolls from a library in the ancient Roman town of Herculaneum have begun to reveal their secrets. The tightly wrapped papyrus scrolls were charred in the disaster, which also destroyed the nearby town of Pompeii. But by studying 3D X-ray scans of the scrolls, researchers have deciphered a word on one of them: "porphyras", meaning "purple". The breakthrough came from Luke Farritor, a 21-year-old computer science student at the University of Nebraska-Lincoln. His success involved training an AI to identify nearly invisible ink-like patterns in the 3D scans. "Seeing Luke's first word was a shock," says Michael McOsker at the University College London in the UK, who was not involved in the discovery.

The eruption of Mount Vesuvius in AD79 laid waste to Pompeii and nearby Herculaneum where the intense blast of hot gas carbonised hundreds of ancient scrolls in the library of an enormous luxury villa. Now, researchers are launching a global contest to read the charred papyri after demonstrating that an artificial intelligence programme can extract letters and symbols from high-resolution X-ray images of the fragile, unrolled documents. Scientists led by Prof Brent Seales, a computer scientist at the University of Kentucky, were able to read the ink on surface and hidden layers of scrolls by training a machine-learning algorithm to spot subtle differences in the papyrus structure captured by the X-ray images. "We've shown how to read the ink of Herculaneum. That gives us the opportunity to reveal 50, 70, maybe 80% of the entire collection," said Seales.