BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Signal Processing and Machine Learning in Art Conservation - Aleks
 andra Pizurica (Ghent University)
DTSTART:20181120T150000Z
DTEND:20181120T160000Z
UID:TALK110455@talks.cam.ac.uk
CONTACT:Carola-Bibiane Schoenlieb
DESCRIPTION:The field of art conservation science and practice relies incr
 easingly on a multidisciplinary research including new sensing technologie
 s and techniques for analyzing a wealth of available data. Multimodal imag
 ing is now routinely employed during the restoration of paintings in order
  to detect more reliably regions or patterns of interest and to support th
 ereby certain decisions that need to be made during the conservation-resto
 ration treatments. In this talk\, we discuss recent advances in digital si
 gnal processing and machine learning for supporting the actual restoration
  of paintings. The focus will be on sparse coding\, representation learnin
 g\, spatial context modelling with Markov Random Fields and Bayesian infer
 ence in tasks such as crack detection\, paint loss detection and virtual i
 npainting. Concrete examples will be shown from the ongoing conservation-r
 estoration treatment of the Ghent Altarpiece.\n\nThe presentation includes
  joint works with Ingrid Daubechies (Duke University)\, Maximiliaan Marten
 s (Ghent University\, Faculty of Arts and Philosophy)\, Bart Devolder (Pri
 nceton University Art Museum)\, Hélène Dubois (Royal Institute for Cultu
 ral Heritage\, KIK-IRPA)\, Bruno Cornelis (Vrije Universiteit Brussel\, El
 ectronics and Informatics – VUB-ETRO) and Ann Dooms (Vrije Universiteit 
 Brussel\, Digital Mathematics group).
LOCATION:MR 14\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR