i'm working on image matching mainly SIFT and SURF for my thesis. i read Moravec's and harris corner detectors and understand them quiet well in my own opinion.A COMBINED CORNER AND EDGE DETECTOR[1]

I even understoond harris-lapace detector but had no luck with understanding it's descriptor.Indexing based on scale invariant interest points[2]

i understood SIFT and SURF too.

what i didn't really understand is some of these topics : harris-laplace descriptor , how does hessian matrix help to detect good interest points , RANSAC(have general idea but need details for image matching) , Haar wavlet( also have a general idea, don't know how it's output look like and how i can work with that)

that's pretty much it. i would really appreciate If anyone can help me with finding general reference for these topics.

(i have sent this question on stackoverflow. they suggest here would be better place to ask it and get proper answer)


1 Answer 1


Check out Szeliski's book: http://szeliski.org/Book/drafts/SzeliskiBook_20100903_draft.pdf

There is also an old book on feature detection: http://www.amazon.com/Feature-Extraction-Processing-Computer-Edition/dp/0123965497

You can read the sections that you care about. Also, I think it is always a good idea to read about scale space theory if you are to work with such algorithms. For example:


  • $\begingroup$ I get a link not found error (404). $\endgroup$ May 23, 2014 at 13:45
  • $\begingroup$ Szeliski's book is very good but not disused Hessian and haar wavelet very much.unfortunately second book that you offer wasn't useful at all. after lots of searching i find some survey about local features which may help others too. $\endgroup$
    – Alireza
    May 23, 2014 at 13:51
  • $\begingroup$ Try it again now. $\endgroup$
    – Alireza
    May 23, 2014 at 13:53

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.