Scientists at Columbia University have developed software that uses photographs (or digital images) of people to determine what the people in the photos are seeing.
The software zooms in on people's corneas and treats them as a hemispherical mirror, then does image-processing to reconstruct the scene being reflected in that mirror. As the NYTimes reports, "the system can automatically recover wide-angle views of what people are looking at, including panoramic details to the left, right and even slightly behind them. It can also calculate where people are gazing - for instance, at a single smiling face in a crowd." High-resolution photos are required for this analysis, unless it's an extreme-close-up: only about 120x120 pixels worth of cornea reflection is required.
The researchers anticipate this technology being used in security cameras and handicap-accessible computer interfaces, among other things.
.
