I need some face similarity metric. I know about PCA,LDA approaches that uses raw pixels data, but they are not scale invariant(I know that I can resize image but I think that's not good solution). Maybe I need to use AAM,ASM aproaches? But I'm interested in metric that gives me the greatest separability of faces. At first I don't need automatic detection of metric features, for example imagine that I can mark all faces by hand.


1 Answer 1


Haven't used them first hand but I'm pretty sure that [SIFT] "Scale Invariant Feature Transform" is scale invariant. And I know that they are used, with great success, in face recognition.

  • $\begingroup$ can you provide example where it used in face detection/recognition task? for example if you try here ipol.im/pub/demo/my_affine_sift to upload 2 faces, it gives no good output. $\endgroup$
    – mrgloom
    Aug 15, 2012 at 7:03
  • $\begingroup$ as I said in the answer, I have never used it, but I know our teacher talked about it in a image recognition course. When I googled on it, it seemed to a couple of versions of the used for example FSIFT. Google is your friend, I only pointed in the right direction. $\endgroup$
    – SlimJim
    Aug 15, 2012 at 17:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.