- From: Jacco van Ossenbruggen <Jacco.van.Ossenbruggen@cwi.nl>
- Date: Thu, 13 Oct 2005 09:53:11 +0200
- To: Jane Hunter <jane@dstc.edu.au>
- CC: "'Giorgos Stamou'" <gstam@softlab.ntua.gr>, "'John R Smith'" <jsmith@us.ibm.com>, raphael.troncy@isti.cnr.it, "'Christian Halaschek-Wiener'" <halasche@cs.umd.edu>, "'Nikolaos Simou'" <nsimou@image.ece.ntua.gr>, "'swick@w3.org'" <swick@w3.org>, Guus Schreiber <schreiber@cs.vu.nl>, swbp <public-swbp-wg@w3.org>
Jane Hunter wrote: > Dear all, > > Unfortunately I can't send emails to the public-swbp-wg discussion list You just did so :-) ... > - I think it would be great to have one use case that involves medical > or scientific images. Medical images in particular are a very > significant category that require domain-specific annotations e.g., > mammography images? > Would you like me to provide a use case for this kind of collection? > Yes please! Can you send it to me in plain text? We agreed in yesterday's teleconf that everyone should send in his contributions before Monday morning Europ time, so if you can make that, than I can put in the next version of the draft. > I've responded to Nikolaos' email about categorization of image > annotation tools. I've missed that mail. Could send it to me again? > A few other suggestions: > > 7) Collaborative or individual > 8) Granularity - file-based or segment-based (and sub-categories of > types of segmentation) Yes, I like those. > 9) Threaded or unthreaded Could you elaborate on this? Is this threaded as in "OS-level multithreaded processing", a "threaded mail client" or something else? > 10) Access controlled or open access Yes, but there may be too many individual, standalone tools to make this an issue for all tools. We have to see. > Also in the tools section you may want to reference: > > 1) Vannotea - a jabber-based system for real-time collaborative > indexing, annotation and discussion of high quality (MPEG-1, MPEG-2, > MPEG-4, JPEG, TIFF, JPEG-2000) images and video. > http://metadata.net/filmed/ > > 2) Rules-By-Example - a graphical user interface that uses examples to > interactively define rules for inferring high level semantic > descriptions of image regions from combinations of low-level > automatically extracted features > http://maenad.dstc.edu.au/papers/2004/iswc2004-rbe.pdf > Will do, thanks a lot, Jacco
Received on Thursday, 13 October 2005 07:53:47 UTC