Ok given my interest in photography, I have a side interest in computational methods for image analysis. Happily the code didn't find wally (cos I think it's a challenge for me that I would rate it as a suitable Turing's test )
But at the end of the page it does offer a solution to implementing your OCR method for rating MCQ exam papers which is fantastic!
And one can even find Mathematica codes online. But most of the those algorithms are based on the idea that we look for similarities with Waldo's face, as described in problem 3 on http://www1.cs.columbia.edu/~blake/'s webpage. You can find papers on that problem, e.g. Friencly & Kwan (2009) (based on statistical techniques, but Waldo is here a pretext to discuss other issues actually), or more recently (but more complex) Garg et al. (2011) on matching people in images of crowds.