Send us a text

To learn more, visit Art Recognition's website.

SHOW NOTES:

2:00 Lisa Salama’s background in art and art law

3:00 authentication remains main risk of art trading

3:30 Salama’s work overseeing legal aspect of Art Recognition and 

4:00 analysis process

4:15 the deep convolutional neural network mimics human brain

5:30 physical inspection of work is not needed

6:00 algorythm assessment determines authenticity

6:15 heat map shows important features that led to network’s decision in red

6:45 Sample report available, e.g., Cezanne’s Boy In Red Vest

7:15 Samson & Delilah confirmed as non-authenticate; listed by National Gallery as a Rubens

8:40 Collaboration with universities 

10:30 data sets

12:00 analysis of paintings and drawings

13:00 analysis of restored work

14:00 legal issues

16:30 data set due diligence process

18:00 minimum 100 works for a data set

19:00 how AI compliments other authentication methods, e.g., art experts

21:00 Unsupervised Deep Learning involves no human programming

21:40 works created by school of an artist

22:30 different styles and periods of an artists’ work

23:00 graffiti

23:20 range of clients

24:00 over 500 case reports completed 

24:10 Future for an Art Recognition app

24:45 co-creator Dr. Carina Popovici 

26:00 how Art Recognition contributes to transparency in art market

28:20 Responsible Art Market

Please share your comments and/or questions at [email protected]

Music by Toulme.

To hear more episodes, please visit Warfare of Art and Law podcast's website.

To leave questions or comments about this or other episodes of the podcast and/or for information about joining the 2ND Saturday discussion on art, culture and justice, please message me at [email protected].

Thanks so much for listening!

© Stephanie Drawdy [2025]