Computer Vision Helps to Copy Keys via Photograph
UC San Diego computer scientists have created an amazing program that can make copies of keys using only an image of the key as the master. They’ve tested this method using a low quality mobile phone camera and also by using a five inch telephoto lens to capture a key image from 200 feet away – and they both worked. Advances in computer vision have made it possible for the program to easily read the individual key cuts from a wide variety of angles and distances.
Stefan Savage, a computer science professor who ran the student project explains:
“This idea should come as little surprise to locksmiths or lock vendors,” said Savage. “There are experts who have been able to copy keys by hand from high-resolution photographs for some time. However, we argue that the threat has turned a corner—cheap image sensors have made digital cameras pervasive and basic computer vision techniques can automatically extract a key’s information without requiring any expertise.”
Professor Savage notes, however, that the idea that one’s keys are sensitive visual information is not widely appreciated in the general public.
“If you go onto a photo-sharing site such as Flickr, you will find many photos of people’s keys that can be used to easily make duplicates. While people generally blur out the numbers on their credit cards and driver’s licenses before putting those photos on-line, they don’t realize that they should take the same precautions with their keys,” said Savage.