X
Get all access to the world's best video surveillance information.
Logo 8fbbe83a6ce128d4940dbb3787cc2aeaf3d9938b15d0b711b17d116501531882
2016 book promo

FAILED: Facial Recognition & Boston Bombing

Author: John Honovich, Published on Apr 20, 2013

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.

Comments (19): PRO Members only. Login. or Join.

Other Reports on Video Analytics

Axis Video Analytics Are Weak on Oct 05, 2015
For more than a decade, video analytics has frustrated and disappointed users. Now, Axis has rel...

Bosch Person / Car / Bike / Truck Analytics Tested on Jun 05, 2015
Automatically identify what objects are persons vs cars vs bikes vs trucks. That is the new featu...

Mark Cuban Funded Video Analytics Company - Netra on Mar 06, 2015
Mark Cuban has funded a video analytics, the second Texas billionaire to take a stake in a survei...

iCetena - This Company Claims to Do What BRS Labs Claims to Do on Nov 10, 2014
In the US, BRS Labs has been the poster boy for outsized marketing. However, BRS Labs' core clai...

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...

Market Guide and Favorite Video Analytics 2014 on Mar 03, 2014
For more than a decade, video analytics has been the great hope for the surveillance industry. In...

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...

Testing Color Analytics Performance on Dec 16, 2013
In an industry known for overhyping its own value, color analytics have been considered pure scie...

VMD Camera Shootout on Oct 28, 2013
Video motion detection's inaccuracy can have disastrous effects on your VMS system, with recordin...

Analytics vs Rain: Axis, Bosch & Sony on Oct 21, 2013
Rain. This was a key objection to our Camera Analytics Test: Axis vs. Bosch vs. Sony. Members rig...


Most Recent Industry Reports

Mega Chinese Electronics Manufactuer Xiaomi Yi Camera Tested on Feb 05, 2016
Xiaomi's revenue is 4 to 5 times larger than Hikvision's. Only in business for 5 years, Xiaomi ha...

Trade Mag Admits 84% Prefer Online Over Print on Feb 05, 2016
Some say the industry is so old and conservative that print is still important. Well, even a pri...

Hikvision Video Analytics Tested on Feb 04, 2016
We tested Hikvision's video analytics on six Hikvision models, ranging from entry level to high e...

Last Chance - IP Networking Course on Feb 04, 2016
Today is the last day to get into the course. Our most popular course starts next week (February...

Add Your Preferred Camera Manufacturer to the Calculator on Feb 03, 2016
One of the most popular features of our Camera Calculator is choosing specific models. Indeed, me...

Axis vs Avigilon vs FLIR vs Hikvision vs Samsung Camera Pricing on Feb 03, 2016
The 'race to the bottom' is a big issue, with average prices dropping sharply over the past few y...

Network Security for IP Video Surveillance Guide 2016 on Feb 03, 2016
Keeping surveillance networks secure can be a daunting task, but there are several methods that c...

Resolution Usage Statistics 2016 on Feb 02, 2016
In the past few years, 4MP, 6MP, 4k (8.3MP) and 12MP cameras have become increasingly commonplace...

Avigilon H4 HD Cameras Released on Feb 01, 2016
Avigilon has announced a new generation of cameras, the H4. In this note, based on speaking with...

Honeywell Pro-Watch Access Control Profile on Feb 01, 2016
Inside we examine Honeywell Pro-Watch access control line: Comparing Honeywell to their compet...