Real or Not Real? Attorney Steven Frank Uses Deep Learning to Authenticate Art

Leonardo da Vinci s portrait of Jesus, called Salvator Mundi, was offered at a British auction for almost half a billion dollars in 2017, making it the most expensive painting ever to change hands.

Even art history specialists were hesitant about whether the work was an initial of the master rather than one of his many protégés.

Steven Frank is a partner at the law company Morgan Lewis, specializing in copyright and commercial innovation law. He s also half of the husband-wife group that utilized convolutional neural networks to identify that this painting was likely an authentic da Vinci.

He talked with NVIDIA AI Podcast host Noah Kravitz about dealing with his better half, Andrea Frank, an expert curator of art images, to verify artistic work of arts with AI s assist.

Secret Points From This Episode:

Confirming art is a fantastic obstacle, as the attributes of a painting that distinguish one artist s work from another s are very subtle. Determining if a piece is authentic requires a very great analysis of a painting s extremely detailed variations.
Using big datasets, the Franks experienced convolutional neural networks to take a look at little, manageable sectors of masterpieces to examine and classify their artists patterns, down to their brush strokes. The model determined that the Salvator Mundi painting sold five years ago is likely the real work of da Vinci.


The most interesting thing about AI research study nowadays is that you can do advanced AI research on an affordable PC as long as it has an NVIDIA GPU. Steven Frank [22:43]

AI might sometimes be wrong, but it will constantly be unbiased, if you train it properly. Steven Frank [10:48]

You Might Also Like:

Researchers Chris Downum and Leszek Pawlowicz Use Deep Learning to Accelerate Archaeology

Scientists in the Department of Anthropology at Northern Arizona University are utilizing GPU-based deep learning algorithms to categorize sherds tiny pieces of ancient pottery.

Wild Things: NVIDIA s Sifei Liu Talks 3D Reconstructions of Endangered Species

Make the AI Podcast Better.

Endangered species can be challenging to study, as they are evasive and the really act of observing them can interrupt their lives. Now, researchers can take a more detailed take a look at threatened types by studying AI-generated 3D representations of them.

Get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn. Drop us a note if your favorite isn t noted here.

Moondust, minerals and soil types are some of the materials that can be quickly recognized and analyzed with AI, based on their images. Migel Tissera is co-founder and CTO of Metaspectral, a Vancouver-based start-up that supplies an AI-based information management and analysis platform for ultra-high-resolution images.

Have a couple of minutes to spare? Complete this listener study. Your responses will assist us make a much better podcast.

AI might sometimes be wrong, however it will always be unbiased, if you train it properly. The most interesting thing about AI research these days is that you can do cutting-edge AI research on a low-cost PC as long as it has an NVIDIA GPU. Have a couple of minutes to spare? Fill out this listener study. Your answers will help us make a much better podcast.

Metaspectral s Migel Tissera on AI-Based Data Management.

Register for the AI Podcast.

Leave a Reply

Your email address will not be published.