Face rec for quality assurance

Edinburgh Airport installs biometric system to track passenger movements (Computerworld UK)

An anonymous facial image is taken of each passenger as they check in and the time it takes each to reach certain waypoints plotted over time. If this time breaches a pre-set parameter for enough passengers, alerts can be generated.

The principle is that moving passengers from check in to the terminal increases their satisfaction with that airport and boosts the amount of time they have to spend money in the retail outlets that generate profit for airports.

The system can also be used to track the movement of passengers through the airport as a whole.

This is another really interesting application for facial recognition technology and, unlike other uses of face technology better described as demographic detection, this one actually is a true face recognition application.

Although it is a true face recognition application, it isn't really an ID application so long as the facial image taken at the time of passenger is not linked to other personal information and it is deleted after the person reaches the "finish line."

The item of interest to airports in this case is the length of time it takes real individuals to travel through various points between check in and the jetway. It's a more sophisticated measure than a simple count and real-world measurement wasn't easily automated before face recognition technology.

Airports in the UK have been early adopters of face recognition for this application because they are held to certain performance metrics (and subject to fines) for airport throughput. Having accurate real-time information on passenger flows can inform on-the-fly staffing decisions. For example, additional security screeners can be dispatched in the event a slow-down is detected, saving passenger time and the airport money.

Though airports have been early adopters, this basic application has obvious utility in shopping malls, department stores, planning for emergency evacuations, and large facility scheduling.

SecurLinx has experience in the design and deployment of this type of system. Our FaceTrac system is readily adapted to the challenge of on-the-fly enrollment, finish-line matching, reporting, and automatically purging image data.

CyberExtruder's Aureus 3D Software Dramatically Increases FaceRec Accuracy

Biometrics in general and facial recognition in particular are getting better all the time and not just because the algorithms are getting better, though they undoubtedly are.

Software companies that organize the data that facial recognition systems use are also making giant contributions to the accuracy and usability of facial recognition systems.

CyberExtruder is one such company. We've worked with them for years and they are the real deal.

Our facial recognition applications use Aureus 3D to enhance face rec accuracy by correcting for oblique angles on either (probe and/or database) side of the identification query.

Aureus 3D is profiled at Officer.com

CyberExtruder released its new Aureus 3D facial reconstruction software, which has shown an increase in facial recognition matching accuracy by 26.5 percent when compared to even the best 2D facial recognition products.

CyberExtruder has also been a devoted and energetic supporter of the non-profit AmberVision Foundation, dedicated to returning missing children to the safety of their family.

Ubiquitious facial-recognition software is coming

Smile, You're On Everyone's Camera (Slate.com)
Slate has a great article on facial recognition technology today.

It takes the baton from yesterday's WSJ article on BI2's MORIS law enforcement technology and provides historical context including our famous FaceTrac project at the 'Snooper Bowl' in 2001.

What I like most about this article is that it acknowledges the dislocations that ubiquitous biometrics (like all new technologies) will cause but recognizes that on net, ordinary people are demanding these technologies and that people will adjust.

Good on author Farhad Manjoo and Slate.com.

Canadian border guards want face rec

Border workers push for biometric screening (CTV News)

Canada's front-line border officers back the idea of a perimeter security arrangement with the United States, with a few caveats.

The Customs and Immigration Union wants more intensive screening of travelers, including a biometric face-recognition tool to pinpoint security threats and wanted criminals.

Facial recognition often gets knocked around a bit because casual observers think it is supposed to function well as an unattended system. Maybe one day it will, but not yet.

That, however, doesn't make it useless. It is a valuable tool in the hands of trained personnel.

Computers don't look at the world the way we do. Whether that's a good thing or not depends on what you're trying to accomplish. For facial recognition in a law enforcement context, it's a good thing to have a radically different point of view applied to a challenge.

First, faces are probably the most meaningful objects in human existence. It's not too much of an exaggeration to say that for millennia human survival has depended upon our abilities at one type of facial recognition: recognizing people you know. Sorting through hundreds of thousands of pictures of people we don't know in order to match the two that are of the same person, however is not something we're inherently good at.

Computers can do that in less than a second, then give the two pictures to a human which is very good at making the single comparison.

The computer does this by treating the face as a mathematical formula. It finds the eyes, then the nose, then other points, measures the distances and angles between the points and turns that all into a long number. Then it does that for everyone in the database. Then it just compares numbers to see which ones come close to matching. It doesn't care about age, race, or gender. It'll match a white man and a black woman. It will match a picture of an old person taken one year ago with a picture of a young person taken today (i.e. a match that's impossible because people don't get younger).

People don't do that. When you ask a person to describe someone they're likely to tell you they were Hispanic, middle aged, round faced, good looking, brown eyes, etc. The computer says: Their eyes were 57.55 mm apart; tip of nose 25 mm below that line 2mm off center to the left, etc.

People and Face Rec make a good team because it's hard to fool them both at the same time. People can't memorize the faces of 1000's of people they don't know & you can fool them by cross-dressing or disguising yourself as a much older person. Computers don't know anything about gender, ethnicity, age or attractiveness, but they can do the math on 1000's of faces in an instant.

Brazilian police to use Face-Rec eye glasses at World Cup

Brazilian police will use futuristic 'Robocop-style' glasses fitted with facial recognition equipment to identify and root out troublemakers at the 2014 World Cup (Telegraph.co.uk)

Major Leandro Pavani Agostini, of Sao Paulo's Military Police, said: "It's something discreet because you do not question the person or ask for documents. The computer does it.

I'd like to know more about this proposed deployment.

UPDATE: Twitter bot Bixby Snyder: I'd buy that for a dollar!
I should have thought of that!

UPDATE II: Since this has gotten so much attention, I think it's appropriate to add a little to this post.

The effective use of facial recognition technology in a surveillance environment requires significantly more training, environmental control (or compensation for environmental factors), and user judgment than other biometric modalities that depend on voluntarily user interaction.

2014 is still a long way away, but I suspect what is being discussed is a re-run of the "Snooper Bowl" experiment featuring our very own FaceTrac in 2001.

If the "Robocops" involved act as anything more than discreet mobile tripods, I'll be surprised.