Return-Path: <sentto-279987-3119-1003455535-fc=all.net@returns.onelist.com> Delivered-To: fc@all.net Received: from 204.181.12.215 [204.181.12.215] by localhost with POP3 (fetchmail-5.7.4) for fc@localhost (single-drop); Thu, 18 Oct 2001 18:40:09 -0700 (PDT) Received: (qmail 11390 invoked by uid 510); 19 Oct 2001 01:38:34 -0000 Received: from n2.groups.yahoo.com (216.115.96.52) by 204.181.12.215 with SMTP; 19 Oct 2001 01:38:34 -0000 X-eGroups-Return: sentto-279987-3119-1003455535-fc=all.net@returns.onelist.com Received: from [10.1.1.220] by n2.groups.yahoo.com with NNFMP; 19 Oct 2001 01:38:56 -0000 X-Sender: fc@red.all.net X-Apparently-To: iwar@onelist.com Received: (EGP: mail-8_0_0_1); 19 Oct 2001 01:38:55 -0000 Received: (qmail 72142 invoked from network); 19 Oct 2001 01:38:54 -0000 Received: from unknown (10.1.10.27) by 10.1.1.220 with QMQP; 19 Oct 2001 01:38:54 -0000 Received: from unknown (HELO red.all.net) (65.0.156.78) by mta2 with SMTP; 19 Oct 2001 01:38:54 -0000 Received: (from fc@localhost) by red.all.net (8.11.2/8.11.2) id f9J1cs506448 for iwar@onelist.com; Thu, 18 Oct 2001 18:38:54 -0700 Message-Id: <200110190138.f9J1cs506448@red.all.net> To: iwar@onelist.com (Information Warfare Mailing List) Organization: I'm not allowed to say X-Mailer: don't even ask X-Mailer: ELM [version 2.5 PL3] From: Fred Cohen <fc@all.net> X-Yahoo-Profile: fcallnet Mailing-List: list iwar@yahoogroups.com; contact iwar-owner@yahoogroups.com Delivered-To: mailing list iwar@yahoogroups.com Precedence: bulk List-Unsubscribe: <mailto:iwar-unsubscribe@yahoogroups.com> Date: Thu, 18 Oct 2001 18:38:54 -0700 (PDT) Reply-To: iwar@yahoogroups.com Subject: [iwar] [fc:Advances.in.face.recognition.software.could.soon.help.shield.airports.and.U.S..embassies.] Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Advances in face recognition software could soon help shield airports and U.S. embassies. By Michael Menduno, October 2001 Issue <a href="http://www.business2.com">http://www.business2.com> A rooftop camera whirs into action as a man crosses the street in front of a U.S. embassy. By the time he's halfway across, an embassy computer has already constructed the man's digital "faceprint" from a series of close-up video images, and has begun comparing it with those of more than 1,000 suspected terrorists in a database. Seconds later an alarm sounds in the security office: According to what the computer "sees" in the man's facial features, there's an 80 percent chance he's a match with a known terrorist. Such are the details, and hoped-for results, of a major government test this month of face recognition technology as a new line of defense against suspected criminals and terrorists. As part of a $50 million project called HumanID, funded by the Defense Advanced Research Projects Agency (DARPA), defense planners are testing one of the most sophisticated face recognition products on the market today -- Visionics Corp.'s FaceIt system -- in hopes that it will eventually shield U.S. facilities here and overseas from terrorist threats. And, if the systems prove themselves decently reliable at long range (up to 500 feet in the case of the DARPA trials), deploying such ID systems at shorter-range security checkpoints in airports may not be far behind. Face recognition systems accounted for only $10 million in sales last year, but recent installations by private industry -- and heightened security fears aroused by the Sept. 11 terrorist attacks -- suggest that the technology is here to stay. Several casinos have begun using the Visionics (<A HREF="aol://4785:VSNX/">VSNX</A>) system to spot known card-counters. Police in Tampa, Fla., have installed 36 Visionics surveillance cameras in a downtown mall to help identify wanted felons and sex offenders. The Israeli Ministry of Defense recently placed an order for the system, which it plans to install at border crossings to verify the identities of Palestinian workers who enter the country each day. Not surprisingly, Visionics stock jumped 143 percent in the week that trading resumed on Wall Street. Under ideal conditions -- using close-up still images, for example -- Visionics claims, its local feature analysis software is as effective an identification tool as fingerprints. But under live conditions -- in which camera angle, lighting, and distance all change by the second -- it's less accurate. In a recent Defense Department test, FaceIt picked the correct person out of a database of 227 faces just 55 percent of the time. Still, it beat out five competing systems, and this month's DARPA trials will further refine its long-range capability. Even if his system proves accurate only half the time, Visionics CEO Joseph Atick says it would pose a deterrent that embassies and airports simply don't have today. "Terrorists aren't going to spend five years planning a mission," he says, "if they have a 50 to 80 percent chance of getting caught." ------------------ http://all.net/ Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
This archive was generated by hypermail 2.1.2 : 2001-12-31 20:59:55 PST