h p wrote:
> (...) Matching of pictures of people's faces entering a football stadium
> (for example) with a database of known "terrorists" (or is it a profile of a
> terrorist?) - and is supposed to be accurate. I can't see why similar
> software can't be used to Find A Similar Video to This Video.
One difference between a face (profile) and a movie is that a movie needs the fourth,
the time dimension. Rhythm of sound, of cuts or fades, of plot points, moods and lights
etc. are things a face doesn't need to be identified as unique. HP, what makes you
comparing these things which couldn't be more different: the one organic, the other
dead? Well, both create and express emotions ? where even the movie is the dead one! But
where a face (persona) meanwhile* can be defined by its eyes' iris only there is still
no way to define a movie by just 1 frame.
(*a prototype was exhibited ca. 1995 at AEC, Austria)
> means that a smarter approach needs to happen.
... and it won't be a technical one. Harry, could you ever note enough words to describe
The Salsa Movie in an adequate way to find you just one of The Similar movies ? without
offering a wrong one?
Roger Howard wrote:
> 2) you must translate your findings into effective controlled vocabularies; in other
words, develop your own semantic standards for describing all the unique aspects of your
content you wish to index.
... and I wonder if any of "your own semantic" would help anybody else except "you"? For
those, I guess, you don't need your own semantic. You need it for all the others.
Harry, are data terrorists, too?
yours,
model T.
_______________________________________________
quicktime-talk mailing list | email@hidden
Help/Unsubscribe/Archives: http://www.lists.apple.com/mailman/listinfo/quicktime-talk
Do not post admin requests to the list. They will be ignored.
