X
Get all access to the world's best video surveillance information.
Logo
Free-book-promo-680-70

FAILED: Facial Recognition & Boston Bombing

Facial recognition vendors have been tripping over themselves to take credit, insert or claim the wonders of their offerings to identify the Boston bombers. However, an excellent Washington Post investigative report cites Boston's Police Commissioner, confirming that:

"Facial-recognition software did not identify the men in the ball caps. The technology came up empty even though both Tsarnaevs’ images exist in official databases."

So what solved the case? A lot of:

"Work [that] was painstaking and mind-numbing: One agent watched the same segment of video 400 times."

Plus, a critical tip from a victim who had seen the bomber face to face:

"FBI agents quickly came to Bauman’s bedside. A man in sunglasses and black baseball cap had walked right up to him, placed a black backpack on the ground and stepped away, Bauman remembered.

His tip became a critical lead, according to law enforcement officials."

A story that should be about the around the clock work of human investigators and the resolve of a man whose legs were torn off has been turned into a promotional campaign for technology vendors.

Technical Barriers to Facial Recognition

The images captured on the street, both from surveillance cameras and smartphones, were not good enough to deliver high accuracy matching. Recall the video from the Lord & Taylor's surveillance cameras, excerpt below:

There's too much downtilt plus the subjects are tending to look the other way, plus the pixel density is too low (standard definition camera with a ~15 foot wide FoV). And obviously the other suspect (#1) was wearing a forward facing cap and sunglasses, causing even more problems.

Note, this does not mean the cameras deployed were necessarily 'bad'. They are sufficient for general monitoring but not for the radically more demanding needs of facial recognition.

Only 'Hollywood' make believe facial recognition could use this.

Ironically, the images from smartphones were of better suitability for facial recognition than surveillance cameras. Here's an excerpt from one of the best ones:

This is obviously from a much wider FoV and the resulting pixel density is too low to deliver accurate facial matching. A fuzzy image of a face may be 'easy' for a human to verify against a specific person/photo but ask a computer to do this against millions of images and it becomes an exercise in futility.


Author: John Honovich, Published on Apr 20, 2013
Comments (19): PRO Members only. Login. or Join.



Other Updates on Video Analytics

ioimage / DVTel Analytic Updates on Feb 20, 2014
In the 4 years since DVTel Acquired ioimage, they have gone quiet but upcoming new products combi...

This Company is "Going To Change the Video Surveillance Market Forever" on Oct 17, 2013
Stop emailing me about this company. All of you. Seriously. In a brilliant marketing campaign, a...

Failed: Surveillance Tech Predictions on Jun 08, 2013
Days before 9/11, MIT's Technology Review released a tour de force review of surveillance technol...

Future of Facial Recognition on May 04, 2013
The Boston Bombings reaffirmed how far facial recognition needs to develop to be an effective sur...

Successful Facial Surveillance Case on Jan 07, 2013
Real time facial surveillance is hard to do - accuracy issues, false alerts, cost and deployment ...

HP Autonomy Fraud Claims on Nov 20, 2012
Massive fraud is revealed in a superstar analytics company -- a lesson that all of us in surveill...

Bad News for Face Recognition (FTC) on Oct 22, 2012
Cold water is being thrown on renewed dreams of using facial recognition and demographic analysis...

License Plate Recognition (LPR) Providers Overview on Oct 09, 2012
License Plate Recognition is the most successful of all video analytic systems (sure, faint prais...

LPR Privacy Problems Reviewed on Oct 02, 2012
The Wall Street Journal has released a detailed investigative report that raises significant conc...


Most Recent Industry Updates

Body Cameras, Poorly Implemented, Failed on Apr 23, 2014
A 2013 study found that body cameras led to a massive reduction in use of force incidents and off...

Advanced Marketing That Avigilon and Dropcam Does But Axis Misses on Apr 22, 2014
This is the technique that two of the fastest growing companies in surveillance use but most incu...

VQiPS - Video Quality in Public Safety on Apr 22, 2014
The Video Quality in Public Safety (VQiPS) working group is run by the US government and is compr...

IR Camera Housing - Raytec Lighthouse on Apr 21, 2014
A key limitation of integrated IR cameras is distance covered. Even long range integrated IR came...

Japanese Stores Facial Recognition Sharing on Apr 21, 2014
A controversy is brewing in Japan after a newspaper was tipped off about a practice stores use to...

How a University Created Its Surveillance Policy on Apr 18, 2014
Some are bad, some are good, some are nonexistent, but what considerations go into crafting a sur...

Video Surveillance At Archaeology Sites Might Surprise You on Apr 17, 2014
What is the camera of choice for securing archaeological sites? We talked to archaeologist Chris ...

Samsung Launching 1280H Analog, Claims HD Quality on Apr 17, 2014
Is analog innovation heating up? 960H was the big analog jump over the last few years, offering ...

Securing Access Control Systems on Apr 17, 2014
Securing access control components is critical to ensuring that a facility is truly secure. Other...

$3,000 Per Classroom School Camera System on Apr 16, 2014
Cameras in schools are nearly everywhere but inside classrooms? Far less common. A school distri...