5
$\begingroup$

I have been doing research on the SIFT (scale invariant feature transform) algorithm, and while I have repeatedly read that in order to detect image features that do not vary with respect to scales of visual perspective, a scale space must be constructed from the source image using repeated Gaussian smoothing and taking differences of those Gaussians. Then local extrema are found in the four dimensional scale space which are designated as scale invariant key points. How this process is performed seems straightforward, but my question is why does this process work at all? What is special about the Gaussain blur that allows us to do this? In the publications that I am reading (listed below), the reason this works is not clear to me.

Lindeberg, Tony. “Detecting Salient Blob-like Image Structures and Their Scales.” Scale-Space Theory in Computer Vision (1994): 249-70. Web. http://www.nada.kth.se/~tony/abstracts/Lin92-IJCV.html

Lindeberg, Tony. “Scale-space.” Encyclopedia of Computer Science and Engineering. Vol. 4. N.p.: n.p., n.d. 2495-504. Web. 16 Oct. 2016. ftp://ftp.nada.kth.se/CVAP/reports/Scale-Space-EncCompSci.pdf

Lowe, David G. “Distinctive Image Features from Scale-Invariant Keypoints.” International Journal of Computer Vision 60.2 (2004): 91-110. Web.

EDIT

I have read many high level explanations of this concept, which generally say that as the sigma of the Gaussian increases, fine grained features should be suppressed and that coarse grained features should be generalizations of fine grained features. But I am looking for a more rigorous and possibly mathematical explanation of why this is the case.

$\endgroup$
  • $\begingroup$ very interesting because I have the exact same question actually ! Like you I understand the process of creation of the scale space (DoG) and finding extrema which is a "simple" mechanical so to speak process, but non of the articles/tutorials etc seem to explain WHY this works ! I am starting to think that nobody really understands it haha ... $\endgroup$ – Machupicchu Feb 4 '17 at 11:34
0
$\begingroup$

If a maximum is found at a given octave X in the original image, then, if we have the scale-invariant property, this maxima will be found on the zoomed down (downscaled) image at octave X-1.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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