AN IMAGE processing system that obscures the position from which photographs are taken could help protestors in repressive regimes escape arrest 鈥� and give journalists 鈥減lausible deniability鈥� over the provenance of leaked photos.
The technology was conceived in September 2007, when the Burmese junta began arresting people who had taken photos of the violence meted out by police against , many of whom were monks. 鈥淏urmese government agents video-recorded the protests and analysed the footage to identify people with cameras,鈥� says security engineer of the Indraprastha Institute of Information Technology in Delhi, India. By checking the perspective of pictures subsequently published on the internet, the agents worked out who was responsible for them.
If a photographer鈥檚 鈥渓ocation privacy鈥� is not protected, their personal safety is at risk, Nagaraja says. This inspired him and security researcher P茅ter Schaffer and computer-vision specialist Djamila Aouada at the University of Luxembourg to find a way of disguising the photographer鈥檚 viewpoint.
Advertisement
Their method is to use graphics processors to artificially create photos taken from a perspective where there was no photographer.
鈥淲e use a computer-vision technique called view synthesis to combine two or more photographs to create another very realistic-looking one that looks like it was taken from an arbitrary viewpoint,鈥� explains Schaffer.
The images can come from more than one source: what鈥檚 important is that they are taken at around the same time of a reasonably static scene from different viewing angles. Software then examines the pictures and generates a 3D 鈥渄epth map鈥� of the scene. Next, the user chooses an arbitrary viewing angle for a photo they want to post online.
The photo then goes through a 鈥渄ewarping鈥� stage, in which straight lines like walls and kerb angles are corrected for the new point of view, and 鈥渉ole filling鈥�, in which nearby pixels are copied to fill in gaps in the image created because some original elements were obscured. The result is pretty convincing, says Schaffer. 鈥淭here are some image artefacts but they are acceptable,鈥� he says (). The team intends to make the software open source.
Matthias Zwicker, a graphics engineer at the University of Bern in Switzerland, thinks the technology is on the right track. 鈥淎nonymising the photographer could be a crucial step in protecting the source of contentious material. I鈥檓 sure this computer-vision technology will evolve into a valuable tool.鈥�
Schaffer鈥檚 team knows it is entering an arms race of sorts: even consumer-level imaging tools could help oppressive regimes. For instance, University of Washington and Google researchers last week that can identify a specific person in every picture in a large set of photos on a website like .
