Where's Waldo?
stackoverflow.com
Where's Waldo?
1–10 of 32 posts
Re: Where's Waldo?
#2Amusing application, but I'd like to see the version that finds Waldo on the page in which everyone is wearing striped shirts
Re: Where's Waldo?
#3Programming potential never ceases to amaze me. I want to learn more. NOW!
Re: Where's Waldo?
#4This is a toy example of the kind of problem that the field of Computer Vision is actively working on: object detection. In a (tiny) nutshell, our best answer for general images and objects is:
1) Instead of using the full color pixel image, use an "edge image" with some simple additional normalizations. If color is important, do this per color channel.
2) Create a dataset with as many cropped examples of the target object as you can find (mechanical turk is useful for annotating large datasets); every other crop of every image is a negative example.
3) Train a classifier (SVM if you want it to work, neural network if you're so inclined) using this dataset.
4) Apply the classifier to all subwindows of a new image to generate hypotheses of the target object location. This can be sped up in various ways, but this is the basic idea.
5) Post-process the hypotheses using context (can be as simple as simply finding the most confident hypotheses within a neighborhood).
If you're interested in object detection, an excellent recent summary of the recent decade of research is due to Kristen Grauman and Bastian Leibe: http://www.morganclaypool.com/doi/abs/10.2200/S00332ED1V01Y2... (do some googling if you don't have access to this particular PDF).
A cool paper from a few months ago that should be mentioned when commenting on a post called "Where's Waldo?" is http://www.cs.washington.edu/homes/rahul/data/WheresWaldo.ht...
Re: Where's Waldo?
#5Amusing application, but I'd like to see the version that finds Waldo on the page in which everyone is wearing striped shirts
In most normal applications, the only thing that would change is what your features are. For example, if you wanted to find Waldo using the shape of his face and/or hat, you would probably just find some SIFT points (or something), and then build an eigenWaldoface, possibly using a PCA'd set of Waldo faces and hats as examples, and then SIFT the image and look for the places that are most like the eigenWaldoface.
This article is not interesting because it's an amazing new algorithm or something that solves some important world problem. It's interesting because it takes something that is not known among the general hacker population for doing this sort of thing really easily, and accomplishes it in a fairly simple way.
Don't be a grump, this is cool. :(
Re: Where's Waldo?
#6This is undoubtedly a data point on the path to the singularity.
Re: Where's Waldo?
#7Something unrelated but perhaps interesting to some people, "Waldo" is actually a localised name for the USA and Canada, his original name is Wally.
Re: Where's Waldo?
#8interesting problem. i'd like to then apply this concept of finding a needle in a haystack to satellite imagery. Using super-computing + giant image data sets, you could theoretically find some pretty obscure stuff if you knew what you were looking for (hidden treasures???).
Re: Where's Waldo?
#9Something unrelated but perhaps interesting to some people, "Waldo" is actually a localised name for the USA and Canada, his original name is Wally. http://en.wikipedia.org/wiki/Where%27s_Wally%3F
It brings me an almost indescribable joy to find that Wally is the original name. Yet I have no idea why.
Waldo always seemed a bit of a strange name, and it still confuses me why it would be changed for the US market. Anyone know why (Wiki doesn't say).
Re: Where's Waldo?
#10Are there other examples of it working? (if there were links, I couldn't see them).
There's a danger of overfitting, where a technique works for one instance (or a subset of instances), but not in general. Detecting stripes could work in general, but as a SO commenter noted, "Where's Wally" images often include spurious stripes to undermine this detection strategy for humans.