Skip to Content

A Photo’s Fingerprint

New software can match images to specific digital cameras.
March 1, 2006

When a gun is used in a crime, forensic investigators identify it by the unique pattern of scratches that its barrel leaves on bullets. A similar trick is now being used to match digital images to the cameras that captured them, an important advance as child pornography crimes increase.

Software developed by Jessica Fridrich at the State University of New York in Binghamton exploits the fact that every digital camera introduces a unique pattern of imperfections, or “noise,” into its images. In monochrome areas, for example, individual pixels might actually be slightly different colors. Fridrich’s software determines a camera’s noise signature by identifying the irregularities in its pictures. That yields a “fingerprint” that investigators can search for in other photos.

Fridrich tested her software using 10 cameras and a total of 3,000 pictures. In every case, the software matched the picture with the right camera, she says. “This is very nice work in the exciting and important problem of camera ballistics,” says Hany Farid, computer science professor at Dartmouth College.

Fridrich is currently seeking a patent and says the FBI is evaluating the technology as an investigative tool. The need is great: between 1996 and 2002, the number of federal cases involving child pornography exploded from 113 to 2,370, and the FBI predicts the trend will continue.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.