Today at 2pm (UK Time) and available over Access Grid (see bottom of the message) as well as at Manchester (sorry about the short notice).
"Digging into image data: answering medieval authorship questions using e-science" Mike Meredith, Humanities Research Institute, University of Sheffield Can adaptive image analytics attribute authorship? And if so how accurate and computationally scalable are they when applied to diverse collections of image data? The topic of authorship is a common research question across multiple disciplines of humanities, arts and social sciences that unites researchers from the field of computational image analysis. The Digging into image data (DiD) project is about collaboratively undertaking e-science research and consists of researchers from the University of Sheffield, Michigan State University and the University of Illinois. For the Sheffield team the work is specifically about identifying the characteristic stylistic, orthographic and iconographic 'signatures' of particular scribes and artists. Research is undertaken through the application of algorithms that include image-edge detection, polygonal model-fitting and geometric comparisons. High-performance computers will also be deployed to facilitate the processing of the large collection of high-resolution datasets. Further Information: http://www.sheffield.ac.uk/hri/projects/projectpages/did_images Friday 15 October, 2-3pm Room 1.10, Kilburn Building, The University of Manchester. ----- If you are interested in giving a seminar or want to suggest a speaker please contact r...@manchester.ac.uk An up to date list of seminars can be found at http://www.rcs.manchester.ac.uk/research/seminars/. RCS is part of the Directorate of IT Services. ---- Anyone wishing to view a seminar via Access Grid should note the following. Please check the Jabber room shortly before the start of the seminar to find if ScreenStreamer is to be used. Virtual Venue: Access Grid Support Centre Virtual Venue: University of Manchester Room1:10 Jabber Room: university-of-manchester-(1.10) (sam.ag.manchester.ac.uk)@conference.mcs.anl.gov ScreenStreamer: Preferably use ScreenStreamer software - go here and select room "University of Manchester (1.10)" from the AGSC section. Grab the screen feed (by clicking on it) from the screenstreamer window and resize it - more info can be found on http://www.memetic-vre.net/software/ScreenStreamer. Alternatively, the screenshot (not animated) can be accessed here (this IP might change for some sessions - please check Jabber). For technical assistance regarding the Access Grid, please contact the Access Grid Support Centre.
