IAPR invited speakers:

Dr. David G. Stork
Computer vision and pattern recognition for the analysis of paintings and drawings: New rigorous methods complement humanistic scholarship in the study of fine art

Dr. Aljoscha Smolic
3D Video and Free Viewpoint Video – Technologies, Applications and MPEG Standards

Computer vision and pattern recognition for the analysis of paintings and drawings:
New rigorous methods complement humanistic scholarship in the study of fine art

Dr. David G. Stork

Ricoh Innovations and Stanford University, USA

www.diatrope.com/stork/FAQs.html

New rigorous methods from computer vision, image processing and pattern recognition have been used to shed light on a number of recent controversies in the study of art. For example, computer fractal analysis has been used in authentication studies of paintings attributed to Jackson Pollock recently discovered by Alex Matter. Computer wavelet analysis has been used for attribution of the contributors in Perugino's Holy Family. Sophisticated computer analysis of perspective, shading, color and form has shed light on David Hockney's bold claim that as early as 1430 Renaissance artists employed optical devices such as concave mirrors to project images onto their canvases. Computer cross-correlation analysis of paintings by Jan van der Heyden shed light on his unusual working methods. Statistical analysis allow the automatic "peeling away" of layers of brush strokes in a digital photograph of a self-portrait by Vincent van Gogh. Computer graphics reconstructions of the tableaus in paintings such as Velazquez' Las meninas, Caravaggio's The calling of St. Matthew, Georges de la Tour's Christ in the carpenter's studio, and Jan van Eyck's Arnolfini portrait allow scholars to explore "what if" scenarios, and thus better understand the working methods of these artists.

How do these computer methods work? What can computers reveal about images that even the best-trained connoisseurs, art historians and artist cannot? How reliable are they for detecting forgeries? How much more powerful and revealing will these methods become? In short, how is computer image analysis changing our understanding of art? This profusely illustrate lecture for non-scientists will include works by many leading painters. You may never see paintings the same way again.

Joint work with Antonio Criminisi, Andrey DelPozo, David Donoho, Marco Duarte, Yasuo Furuichi, Mohammad Irfan, Micah K. Johnson, David Kale, Ashutosh Kulkarni, Petria Noble, M. Dirk Robinson, Silvio Savarese, Morteza Shahram, Ron Spronk, Christopher W. Tyler, Lisa Wong and Li Zhang

Dr. David G. Stork is Chief Scientist of Ricoh Innovations and Consulting Professor of Statistics at Stanford University, where he has held appointments in the departments of Computer Science, Electrical Engineering, Statistics, Psychology and Art and Art History. He is a Fellow of the International Association for Pattern Recognition and has published in optics and art for over two decades, including Seeing the Light: Optics in nature, photography, color, vision and holography (Wiley), the leading textbook on optics in the arts. A graduate in physics of the Massachusetts Institute of Technology and the University of Maryland at College Park, he also studied art history at Wellesley College and was Artist-in-Residence through the New York State Council of the Arts. He has taught courses such as "Optics, perspective and Renaissance painting," and "Computer vision and image analysis in the study of art," over the last quarter century variously at leading liberal arts and research universities such as Wellesley College, Swarthmore College, Clark University and Stanford University. He holds 38 US patents and has published numerous technical papers on human and machine learning and perception of patterns, physiological optics, image understanding, concurrency theory, theoretical mechanics, optics, image processing, as well as six books or proceedings volumes, including Pattern Classification (2nd ed.), the world's all-time best-selling textbook in the field, translated into three languages and used in courses in over 250 universities worldwide and co-editor of Computer image analysis in the study of art (SPIE 2008), the first symposium volume on the topic. He has served on the editorial boards of five international journals and has delivered over 59 plenary, invited or distinguished lectures at universities and conferences (atop nearly 200 traditional invited colloquia and seminars). He created the PBS television documentary 2001: HAL's Legacy based on his book HAL's Legacy: 2001's computer as dream and reality (MIT).

top

3D Video and Free Viewpoint Video – Technologies, Applications and MPEG Standards

Dr. Aljoscha Smolic

Disney Research, Zurich, Switzerland

http://iphome.hhi.de/smolic/

An overview of 3D video and free viewpoint video is given with special focus on related standardization activities in MPEG. Free viewpoint video allows the user to freely navigate within real world visual scenes, as known from virtual worlds in computer graphics. 3D video provides the user with a 3D depth impression of the observed scene, which is also known as stereo video. In that sense as functionalities, 3D video and free viewpoint video are not mutually exclusive but can very well be combined in a single system. Research in this area combines computer graphics, computer vision and visual communications. It spans the whole media processing chain from capture to display and the design of systems has to take all parts into account. The conclusion is that the necessary technology including standard media formats for 3D video and free viewpoint video is available or will be available in the future, and that there is a clear demand from industry and user side for such new types of visual media.

Aljoscha Smolic recently joined Disney Research, Zurich as Senior Research Scientist and Group Leader "Video of the Future". He is also teaching at ETH Zurich. Before he was Scientific Project Manager at the Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institut (HHI), Berlin, and Adjunct Professor at the Technical University of Berlin. He has conducted research on the border line of video processing, video coding, computer vision and computer graphics and is specifically a renowned researcher in the area of 3D video and free viewpoint video. He published more than 90 papers in scientific journals and conference proceedings. In this context he has been involved in MPEG standardization activities. He chaired the MPEG 3DAV group pioneering standards for 3D video and is among the editors of the Multiview Video Coding (MVC) standard.

Dr. Smolic received the "Rudolf-Urtlel-Award" of the German Society for Technology in TV and Cinema (FKTG) for his dissertation in 2002. He is Area Editor for Signal Processing: Image Communication and Guest Editor for IEEE Transactions on CSVT and IEEE Signal Processing Magazine. He is Committee Member of several conferences, including ICIP, ICME, 3DTV-CON and EUSIPCO.

top