> > 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? -- http://mail.python.org/mailman/listinfo/python-list
