image matching algorithms

[Daniel Fetchinson]

> >>> There are a number of free tools for image matching but it's not very
> >>> easy to decipher the actual algorithm from the code that includes db
> >>> management, GUI, etc, etc. I have my own image database and GUI so all
> >>> I need is the actual algorithm preferably in pseudo code and not in
> >>> the form of a research paper (from which I also found a lot but since
> >>> I'm not that much interested in the actual science of image
> >>> recognition this seems like an over kill).
> >>>
> >> I'd recommend SIFT. There's quite a bit of information on SIFT. In most
> >> cases, they don't cover the background science too much, but are still
> >> heavy on the math. Pseudo code is hard to come by since it will take
> >> many lines of pseudo code just to express one concise mathematical
> >> equation. There are however many links to implementations in various
> >> languages on the Wikipedia page.
> >>
> >> http://en.wikipedia.org/wiki/Scale-invariant_feature_transform
> >>
> >> I have had good experiences with SIFT for feature extraction from images
> >> (I have used it for panorama stitching and robot mapping). It's
> >> insensitive to scale and rotation. Note that it is a patented algorithm
> >> and this may (or may not) pose a problem for you.
> >>
> >
> > Thanks for the info! SIFT really looks like a heavy weight solution,
> > but do you think the whole concept can be simplified if all I needed
> > was: given a photo, find similar ones? I mean SIFT first detects
> > objects on the image and find similarities, but I don't need the
> > detection part at all, all I care about is similarity for the whole
> > photo. I surely don't understand the big picture fully but just have
> > the general feeling that SIFT and other expert tools are an overkill
> > for me and a simplified version would be just as good with a much more
> > easily comprehensible core algorithm.
> >
> > Or am I being too optimistic and there is no way out of going into the
> details?
> >
>
>
> Using the histogram of the picture may be good enough for your
> application. Here's something I put together for comparing images (for
> purposes of detecting motion) taken by the built-in web cam in my
> Macbook Pro. This might be good enough if you play with the threshold.
>
>
> """
> I'm writing a simple little app for doing motion detection with data
> output from wacaw, a package for MacOSX. You could easily modify this
> script to get data output from some other source.

Thanks Shane, this is simple enough indeed, which is great. I'll give
this a try and maybe it'll be good enough for me.