Police Can Trace Cameras Thanks to Sensor Imperfection ‘Fingerprints’

camera noise to help fight crime

Computer scientists at the University of Groningen have created a system to analyze the noise produced by individual cameras to help law enforcement fight child exploitation.

Groningen is a city in the Netherlands, which is the biggest distributor of child sex abuse images in the world. To fight this type of exploitation, forensic tools are needed to analyze digital content from the cameras.

The researchers believe that camera noise is an untapped source of information that can be used to fight crime, reports Lab Manager.

As part of an EU project, University of Groningen computer scientists, together with colleagues from the University of Leon in Spain, have found a way to extract and classify the noise from an image or a video that reveals the “fingerprint” of the camera with which it was made.

“You could compare it to the specific grooves on a fired bullet,” says George Azzopardi, assistant professor in the Information Systems research group at the Bernoulli Institute for Mathematics, Computer Science, and Artificial Intelligence at the University of Groningen.

“Each firearm produces a specific pattern on the bullet, so forensic experts can match a bullet found at a crime scene to a specific firearm, or link two bullets found at different crime scenes to the same weapon.”

“Every camera has some imperfections in its embedded sensors, which manifest themselves as image noise in all frames but are invisible to the naked eye.”

The team developed a system to extract and analyze camera noise by utilizing image recognition classifiers.

“They are used to extract information on the shapes and textures of objects in the image to identify a scene,” says Guru Bennabhaktula, a Ph.D. student both in Groningen and Leon. “We used these classifiers to extract the camera-specific noise.”

Bennabhaktula says that noise can be unique to a brand of cameras, to a specific type, and to individual cameras. He used the publically available VISION dataset and the Dresden dataset and used them to train a convolutional neural network.

From this, he was able to achieve 99 percent accuracy when classifying 18 camera models using images from the Dresden dataset.

It all forms part of an EU project, called 4NSEEK, in which scientists and law enforcement agencies collaborate to develop intelligent tools to help fight child exploitation.

Azzopardi outlines the potential advantages the system has. “If the police find a camera on a child abuse suspect, they can link it to images or videos found on storage devices.”

“By using only five random frames from a video, it is possible to classify five videos per second. The classifier used in the model has been used by others to distinguish over 10,000 different classes for other computer vision applications,” adds Bennabhaktula.

This means that the classifier could compare the noise from tens of thousands of cameras. The 4NSEEK project has now ended, but Azzopardi is still in touch with forensic specialists and law enforcement agencies to continue this research line.

“And we are also working on identifying source similarity between a pair of images, which has different challenges. That will form our next paper on this subject.”

Camera noise is also used in the project ToothPic, which aims to help photographers fight copyright infringement.

Image credits: Header photo licensed via Depositphotos.