Visionics unmasks face-recognition tech

Looking to expand its reach in the federal market, face-recognition vendor Visionics Corp. last week released a product that allows users to sift through huge databases of facial images to find a match for a particular individual.

The new product, called FaceIt DB, is designed to allow federal officials who have a photo of an escaped felon, for example, to search thousands of photos collected by security cameras to find a match— what is known as a one-to-many search.

The company sees the intelligence community and the law enforcement community as the primary government markets for FaceIt DB, said Joseph J. Atick, president of Visionics, Jersey City, N.J. "As an investigation tool, it's invaluable," he said. "This tool should enable [investigators] to conduct better and fast-er investigations."

Visionics' face-recognition technology is based on an algorithm that analyzes facial geometry, comparing measurements between different parts of the face.

FaceIt DB differs from the company's other face-recognition products in that it does more than simple identification verification. Visionics' ID verification products are used largely to control access to things such as computers by verifying that the face of the person using the computer matches the photo of the person who is authorized to use the machine.

Several agencies, such as the Immigration and Naturalization Service, the National Security Agency and the Army Research Laboratory, already have begun to experiment with Visionics' products for access to computers or buildings.

Atick hopes the new product will bring in even more federal customers, particularly in law enforcement. Besides working with images supplied by video cameras, the new product can tap into photo databases, such as those maintained by state motor-vehicle departments.

Agencies using face recognition have high expectations, but most agencies remain in an exploratory mode, users and analysts said.

"Face recognition is one technology that appears promising in providing a layered security approach for preventing unauthorized access" to national security systems, an NSA spokeswoman said.

The INS also is experimenting with face recognition, using the technology for ID verification to accelerate security checks at a border crossing near San Diego. "We're testing right now. We have high anticipation that it's going to be a good thing," said Ronald W. Collison, associate commissioner for information resources management at the INS.

But some observers are still wondering about the accuracy of face-recognition products.

"I think that [accuracy of one-to-many] still needs to be proven," said Jackie Fenn, vice president and research director of advanced technologies at Gartner Group. "But it's still somewhat early, without having large deployed applications that really test that ability."

FaceIt DB, available directly or through resellers, costs $5,000 to $50,000, depending on the level of customization that a customer needs.


  • Defense
    Ryan D. McCarthy being sworn in as Army Secretary Oct. 10, 2019. (Photo credit: Sgt. Dana Clarke/U.S. Army)

    Army wants to spend nearly $1B on cloud, data by 2025

    Army Secretary Ryan McCarthy said lack of funding or a potential delay in the JEDI cloud bid "strikes to the heart of our concern."

  • Congress
    Rep. Jim Langevin (D-R.I.) at the Hack the Capitol conference Sept. 20, 2018

    Jim Langevin's view from the Hill

    As chairman of of the Intelligence and Emerging Threats and Capabilities subcommittee of the House Armed Services Committe and a member of the House Homeland Security Committee, Rhode Island Democrat Jim Langevin is one of the most influential voices on cybersecurity in Congress.

Stay Connected


Sign up for our newsletter.

I agree to this site's Privacy Policy.