This Professor Can Tell From the Pixels That Your Photo’s Been ‘Shopped
A new software package can figure out if a photo has been ‘shopped or not
Once, manipulating photography required extensive experience in the darkroom, dodging and burning, cropping and pasting, double-exposing and solarizing. Thanks to digital editing programs like Photoshop, the breadth of knowledge required to pull off a convincing edit has shrunk drastically. Photoshop controversies abound, but now an image forensic scientist thinks he can put a stop to heavily edited images masquerading as legitimate photographs with a program called FourMatch, reports The New York Times.
Every time you take a picture, your camera automatically affixes it with a wealth of behind-the-scenes data: the date and time, the camera’s model, the shutter speed, aperture, and lens used, among others. By drawing on all of this information, along with much more, FourMatch “determines the likelihood that an image has been altered by comparing the digital “signature” of an image with a database of more than 70,000 known signatures for cameras, smartphones, software and online services, from social networks like Facebook to photo-storing sites like Picasa.”
The Times:
The many signatures arise from the malleability of the JPEG standard, the format in which nearly all cameras save images. Different cameras and mobile devices have varying sensor sizes and resolution settings, and techniques for handling thumbnail pictures and image metadata. Different cameras and software use different methods to compress image files. All leave telltale digital tracks.
So, with a wide database of “signatures” from certain cameras, created under certain conditions, the software lets you know whether the photo you’re looking at is realistic or if it’s been heavily processed.
More from Smithsonian.com: