"The program is simple. You have to click on the photo to tell it where the top of the key is, and a few other control points. From here, it normalizes the key's size and position. Since each pixel then corresponds to a set distance, it can accurately guess the height of each of the key cuts," explained Benjamin Laxton, the first author on the paper who recently earned his Master's degree in computer science from UC San Diego.The researchers have not released their code to the public, but they claim that anyone with a decent working knowledge of MatLab and computer vision techniques could create a similar system without much difficulty. Their suggestion: treat your keys like you would a credit card. Thanks for giving us all one more thing to worry about guys. [Sneakey via USCD via Slashdot]
There are skilled locksmiths out there that can reproduce a key from high-resolution images, but new software developed by computer scientists at UC San Diego has simplified the process to a frightening degree. In fact, their "Sneakey" system can reproduce a key with only a grainy cellphone image or, in one case, a picture taken from 200 feet away with a five-inch telephoto lens.