Police can trace cameras through sensor imperfection ‘fingerprints’

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

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

Researchers believe camera noise is an untapped source of information that can be used to fight crime, reports Laboratory manager.

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

“You can compare it to the specific grooves of 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 gun produces a specific pattern on the bullet, so forensic experts can match a bullet found at one crime scene to a specific gun, or link two bullets found at different crime scenes to the same armed.”

“Each camera has imperfections in its built-in sensors, which manifest as image noise in all frames but are invisible to the naked eye.”

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

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

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

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

It’s all part of an EU project, called 4NSEEK, in which scientists and law enforcement work together to develop smart tools to help tackle child exploitation.

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

“Using just 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 noise from tens of thousands of cameras. The 4NSEEK project is now complete, but Azzopardi is still in contact with forensic and law enforcement specialists to continue this line of research.

“And we are also working on identifying source similarity between a pair of images, which presents different challenges. This will form our next article on this topic.

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

Picture credits: Header photo licensed via Depositphotos.

Comments are closed.