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

Gun Detection Analytics Are Here, Says Startup on Jul 03, 2014
A timely innovation, or cashing in on tragedies? A new video analytics company is touting its 'g...

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...


Most Recent Industry Updates

Monday! IPVM Member Orientation September 2014 on Sep 22, 2014
We are holding a live call / webinar this Monday showing you how to get the most out of your IPVM...

Milestone Launches DVRs on Sep 19, 2014
So much for innovation and the open platform, Milestone has entered the DVR business. In this no...

Genetec Adds IP Telephony (Sipelia) on Sep 19, 2014
Why would one of the biggest VMSes get into Voice over IP? That is the big question as Genetec h...

New Product: Software House Mega Controller on Sep 18, 2014
Software House's new controller, iStar Ultra, doubles the number of doors typically supported, fr...

World's First (And Only) Intrusion Detection Keypad Guide on Sep 18, 2014
Arming and disarming are the most fundamental tasks in intrusion systems. Keypads are the most co...

New HD Video Analytic Cameras (ioimage / DVTel) on Sep 17, 2014
DVTel is releasing their first HD video analytic cameras, nearly 5 years after acquiring ioimage....

New Audio Surveillance Device Eliminates 3 Cables (Louroe) on Sep 16, 2014
Adding audio to IP surveillance systems can be a pain, often requiring a completely separate set ...

3D Camera Design Training Class on Sep 16, 2014
Below is an 87 minute recorded training class video that shows you how to do 3D camera designs, i...

Manufacturers Sound Off on ONVIF on Sep 16, 2014
ONVIF has achieved massive adoption amidst significant criticism. The most vocal critics are typi...

Live From ASIS 2014 Call on Sep 15, 2014
On Monday September 29th at 8pm ET, after the first day of ASIS exhibits, IPVM will host a live w...