Next Generation Identification: FBI Launches Facial Recognition Project
By David Tobia
September 12, 2012
September 12, 2012
- The FBI will devote $1 billion to its Next Generation Identification program. The facial recognition program will include iris scans, DNA analysis and voice identification, reports New Scientist.
- The FBI hopes to use facial recognition data from existing mugshots to help track suspects in crowds. The agency can also scan existing mugshots for matches with new arrests.
- “Another application would be the reverse,” explains the article. “Images of a person of interest from security cameras or public photos uploaded onto the Internet could be compared against a national repository of images held by the FBI.” This technology could help police find new leads in cases.
- Privacy advocates argue against the FBI’s plans, noting that the Next Generation Identification program’s privacy statement does not clearly state that only known criminals will be included in the database.
- Existing algorithms have achieved facial recognition accuracy of up to 92 percent when dealing with as many as 1.6 million mugshots.
- Carnegie Mellon researcher Marios Savvides created an algorithm that can “analyze features of a front and side view set of mugshots, create a 3D model of the face, rotate it as much as 70 degrees to match the angle of the face in the photo, and then match the new 2D image with a fairly high degree of accuracy,” explains New Scientist.
- The largest obstacle facing the FBI may be low light situations. Researchers have had difficulty matching faces in dimly lit situations. Although infrared cameras allow more accuracy, they are expensive.
No Comments Yet
You can be the first to comment!
Leave a comment
You must be logged in to post a comment.