New Software Can Distinguish a City's DNA

Jacob Aron reports on the promising new software developed by an international group of researchers that can recognize "what makes Paris look like Paris."
June 10, 2012, 1pm PDT | Jonathan Nettler | @nettsj
Share Tweet LinkedIn Email Comments

Researchers from Carnegie Mellon University in Pittsburgh and INRIA in Paris have written software that can recognize the unique architectural features that can distinguish one city from another. 

According to Aron, "The researchers selected 12 cities from across the globe and analysed 10,000 Google Street View images from each. Their algorithm searches for visual features that appear often in one location but infrequently elsewhere...It turns out that ornate windows and balconies, along with unique blue-and-green street signs, characterise Paris, while columned doorways, Victorian windows and cast-iron railings mark London out from the rest. In the US, long staircases and bay windows mean San Francisco, and gas-powered street lamps are scattered throughout Boston."

According to the researchers, "The discovered visual elements can also support a variety of computational geography tasks, such as mapping architectural correspondences and influences within and across cities, finding representative elements at different geo-spatial scales, and geographically-informed image retrieval."

The team will present their work at the SIGGRAPH graphics conference in Los Angeles in August.



Full Story:
Published on Friday, June 8, 2012 in New Scientist
Share Tweet LinkedIn Email