Mirror Image

Mostly AR and Stuff

Video Surveillance is Useless

Found this interesting slide presentation form Peter Kovesi, inventor of phase congruency edge detector. It basically saying, that on current tech level video surveillance is useless for face identification. What follow is that it’s actually harmful, due to wrong impression of it’s reliability.
Also on his page – some fun animation or How to Animate Impossible Objects
impossible
PS Fourier phase approach to feature detection looks really promising, especially if to find some low computation cost modification.

Advertisements

18, July, 2009 - Posted by | computer vision | , , , ,

3 Comments

  1. dont you think in real life people use multiple “frames” to recognize other people as well as other clues, too? it is far easier to recognize other people “live” than to find them in crowd in some picture.

    Comment by makc | 18, July, 2009

  2. Actually I myself always had a problem with face recognition, even face to face. It may means there is some kind of hardwired neural net in brain responsible for process, some kind of Bayesian network may be. The point is – not only computers have this problem )))

    Comment by mirror2image | 18, July, 2009

  3. sure thing, there is a medical condition causing people to lose their face recognition completely – prosopagnosia

    Comment by makc | 18, July, 2009


Sorry, the comment form is closed at this time.

%d bloggers like this: