Kae Verens has posted a cool little application of how to pull information out of a photo and parse it with the GD library. His example is a visual sudoku solver (part one, at least).
The plan for this one is that, if you’re doing a sudoku puzzle in the pub or on the train, and you get stuck, you just take a snapshot of the puzzle with your camera-phone, send the photo to a certain mobile number, and a few seconds later the solution is sent back as an SMS message. The solution costs you something small - 50 cents, maybe.
The script looks at a picture of a sudoku puzzle, converts it to b&w and tries to find the squares surrounding each position of the board. With these measurements, the next step is to grab the numbers already in the puzzle and hand those off to the puzzle solver to be processed.