Google has acquired PittPatt also known as Pittsburgh Pattern Recognition, an off-spin from a 2004 Carnegie Mellon University project which dealt with object recognition. PittPatt can be used for finding faces in images, categorizing faces by recognizing if the faces are the same person, finding faces in video and finding points of interest on a face (eg. eyes and base of nose).
PittPatt told website visitors that “at Google, computer vision technology is already at the core of many existing products (such as Image Search, YouTube, Picasa, and Goggles), so it’s a natural fit to join Google and bring the benefits of our research and technology to a wider audience.” They said that the PittPatt technology could be used in mobile applications, video and images.
It is likely that the technology will be added to Google+. Google has previously stopped a plan to include facial recognition in Google Googles after privacy concerns. Facial recognition is already available in Google Picasa software.
In 2006, PittPatt was selected as a contractor for the U.S. Disruptive Technologies Office as part of Phase III of the Video Analysis and Content Extraction (VACE) program. PittPatt received over $2.1 million for “object recognition and tracking in video, particularly robust recognition of faces in low resolution, low quality video” according to archived news information and stopped in 2009. In 2007, PittPatt was issued a patent for an “object finder for two-dimensional images, and system for determining a set of sub-classifiers composing an object finder.”
PittPatt have said that “given our face mining output, it took a person less than five minutes to assign names to all the main characters (Kirk, Spock, Mccoy, Uhura, Scotty, Sulu and Chekov) and a couple of minor ones (Janice, Nurse Chapel) across all 67 episodes”, in a now removed webpage about the capabilities of PittPatt’s face mining technology tested over three seasons of Star Trek.