Researchers have developed an algorithm that can look at photographic images and determine where in the world the picture was taken.
Such capability could have numerous applications such as enhancing online image search techniques or helping users find family photos from a specific trip or even forensic purposes. Determining the location of photos also makes it possible to combine them with geographic data bases related to climate, population density, vegetation, topography and land use, researchers said.
The IM2GPS algorithm developed by Carnegie Mellon University computer science graduate student James Hays and Alexei Efros, assistant professor of computer science and robotics, doesn't attempt to scan a photo for location clues, such as types of clothing, the language on street signs, or specific types of vegetation, as a person might do. Rather, it analyzes the composition of the photo, notes how textures and colors are distributed and records the number and orientation of lines in the photo. It then searches GPS-tagged images in Flickr for photos that are similar in appearance, researchers said.
The researchers said they could accurately geolocate the images within a mile for 16% of more than 200 photos in their test set - up to 30 times better than chance. And even if their algorithm failed to identify the specific location, they often found that it could narrow the possibilities, such as by identifying the locale as a beach or a desert.
The IM2GPS algorithm located photographs of such landmarks as the Cathedral of Notre Dame in Paris. It was also able to recognize that a narrow street in Barcelona was typical of Mediterranean villages, rather than an alleyway in the US, researchers said.
Researchers also noted that some odd matches also occurred. The architecturally unique Sydney Opera House seemed to the computer to be similar to a hotel in Mississippi as well as a bridge in London. A shot of the Eiffel Tower at dusk was matched to other Eiffel Tower shots, but also to San Francisco's Coit Tower and New York's Statue of Liberty, both shot at dusk. One reason for this confusion is that the algorithm is not designed to recognize specific objects so much as it is to recognize geographic areas, Hayes said. For instance, an image of Utah's Monument Valley caused the IM2GPS algorithm to successfully retrieve a number of other images from Monument Valley and the American Southwest, rather than images of a specific rock formation.
Layer 8 in a box
Check out these other hot stories: