After finding itself in hot water with privacy advocates, Google has
begun obscuring the faces of people in its Street View service, which
lets users of Google Maps zoom in to view street level images. But the
images look decidedly odd, with whole streets peopled by blurred faces.
It
needn't be this way, says Neeraj Kumar of Columbia University, New
York. Kumar and his colleagues have developed software that gives
everyone a face - just not their own. The software randomly selects
33,000 photos of faces from picture-sharing sites like Flickr.com, then
picks the most suitable faces for each person in shot. Only the eyes,
nose and mouth are used, resulting in a composite image of the two
people. "It matches subject pose, lighting conditions and image
resolution," says Kumar. "The selected faces are aligned to common 3D
coordinates, corrected for colour and lighting, and blended into the
target image."
The end result is a convincing face rather than a blur, although the team's images (pdf link here)
can be spooky, especially when people get features from the opposite
sex. What's more, the software works automatically. "Previous face
replacement software required manual assistance, much like editing an
image in Photoshop," says Kumar.
No comments:
Post a Comment