BBC Featured Deep Learning Face Recognition Analyzed (Digital Barriers)

Author: Brian Karas, Published on Aug 30, 2017

The UK's largest broadcaster, BBC, recently featured Digital Barriers (also based in the UK) on a segment highlighting face recognition technology. The TV segment showed Digital Barriers' SmartVis Face being used to monitor public spaces for appearances of "terrorist watchlist" suspects.

Digital Barriers claims the use of deep neural networks is extending the capabilities of their SmartVis Face product, allowing them to achieve new levels of performance and accuracy.

This report analyzes the SmartVis product, based on conversations with Digital Barriers, and outlines where the company says the product has made advancements, and where limitations still exist in facial recognition.

*** **'* ******* ***********, ***, ******** ******** ******* ******** (**** based ** *** **) ** * ******* ************ **** *********** technology. *** ** ******* ************* ********' ******** ********* **** ** ******* ****** ****** *** *********** ** "********* watchlist" ********.

******* ******** ****** *** *** ** **** ****** ******** ** extending *** ************ ** ***** ******** **** *******, ******** **** to ******* *** ****** ** *********** *** ********.

**** ****** ******** *** ******** *******, ***** ** ************* **** Digital ********, *** ******** ***** *** ******* **** *** ******* has **** ************, *** ***** *********** ***** ***** ** ****** recognition.

[***************]

SmartVis ********

********** ******* ********' ***** ********* ******* ****.******** ****** *** ******-*********** *********, ***** ** ***** ** ********** ******* Barriers******** **** **************** ****. ***** **** ***********, *** ******* **** **** **** re-engineered *** ******** ** *** ********, ********* *********** * **** learning ***** ** *** ****** ** ****** ****** ***** ** non-optimal **********.

******** **** ** * ******-***** ******, ********* ******* **** ********* cameras ** **** ****, *** ********** ****** ** **** ***** on ************* ******** *** ******** (** *** ********) * **** against * ******** ** ******** *****.

Deep ******** ***********

******* ******** ****** **** **** **** * **** ******** ******** to ***** * ****** ******* ** ********* ***** ** ******** distinctive ******** **** ************* ******* *****. **** ** ** ******** to *********** ******* ***** ********* **** ** ******* ********** *** distances ******* ******* ********** ** * **** (*.*.: ******* ******* eyes, ******** ******* **** *** ****, ***.).

*** **** ******** ******** ****** **** ** **** * *****, or * **** ** * ***** ****** ** ******** ** previous ********. **** **** ******* ****** ******** ***** **** *** view ** *** **** ** ************* ********* **** *** *****(*) used ** ****** ** ** *** ********.

* ***** **** ** ******* ****** ******* ****** ** *****, instead ** **** **** * ****** "**** ****", ***** ******* Barriers ****** **** *********** ** ********* ******** ** *** ******, and *** ***** ** ********, ** *** ****** ***** **** multiple ***** ** *** ****, ********** ********* **** **** *** the ******** ********* ** *******.

******* ******** ****** ***** ************ ***** *** ******* **** ****** for "***-*********" ********, ***** * ****** *** *** ** ***** a ****** *********** ****** ** ** ***, *** **** *** not ***** ** "******" **** *** ****** ** ******* ******** at * ****** ** ******* ******* * **** ******* ***** point.

Field ** **** **************

*** ********* ***** * ******* ** ** ****** ******* *** eyes (~*** *** / ~*** ***) *** ******** ***********, *** will *** ******** *********** ************ ** ** ** ****** ******* the ****, **** ****** ******* (*.*.: ** ******) *** ******** any ********** ******* ** ********.

** ** * ***** ** *** ***** ** **** *** be ************** ********.

***** ***** ** ** *********** ******* ********** *********, *** * face ***** *** ***** ************ ********* **** ** ********* ***** 1080p *******.

Enrolling *****

***** *** ** ******** ** *** ******** **** ****** ****** uploaded ("********"), **** * ****** ******** ** * **, ** from ** **** ***** ********. *******, ******** *****/****** ** *** face *** ******** *** ******* ******** ** ******** *** ******/**** later.

Server ************

******** **** **** ** ** *****/******* ***** ******** (** ** i7 *********), *** **** **** ** ********** *** **** ****** network *********. ******* **** ********* *** **** ******** *****.

***** ****** ************ **** **** ***** ** *** ****** ** channels, **** ** *** ******** ***** ********, *** *****/****** ***** desired ** *** ********. ** ******* ****** **** * ****** GTX **** **** ** ********* *** * *******, **** * database ** ~*,*** ***** *** ****** ***** ******* ** ****-**** (<1 ******). ********** **** *** ** ***** ** ****** **** streams **************, *** *** *** *** ************ *** ******** *** large ********* ** ************ **** **** **** ********** ** ******.

*******

***** ****** **** ~$*,***-$*,*** *** *******/******, ********* ********* ** *** size ** *** ****** ******** *** ******** ***** ** ********. The $*,*** ***** ** **** ******, ********* ** ******* ********, for ********* ******* ********** ** *** ***** ** ******* ******* to ~*,*** *****.

Sales *******

**** **** *******************, ******* ******** ***** *** ******** ********* ******* ******** ******** integrator ******** ********.

Software - **** ******** *** ** ********

***** ******** **** **** ******* * "**********" **** *********, ********* to ******* ********, **** ********* *** *** ******* **** ** an ****** **** ****** * *** ***** **** *********, ***** could ** * ***, ** **** ***** ***********-******** ********. ******* Barriers **** **** ************ **** ***** **** ********* *** *******, as **** ** **** **** *********, *** *** **** ****** customers **** ****** ***********, ** ******, *** ********** *****. *** company ****** **** *** ** *** ******* ** ***** ******** base ***** ****** ** ** "********" *******, *** **** ***** should ****** **** ****** ** ****** *********** ** **** ***********.

*** ******* **** **** *** ******* ** * *** ******** release **** **** **** **** ************ ** *** *****-***** ******* to **** ** ********* ** * ******* ******** ****.

Upcoming ********

******* ******** **** **** *** ******* ** ********* ***-**** ******* is ** *********** *** ****** **** ****-********. **** ** **** intended ** ***** ** ** ********** **** * ****, *** more ** ** ***** ****** ** ***** **** *********** ** things **** *********** ** ** *****/******** ******, ** ******** **** to ******, ***.

Face *********** **********

**** *********** ******* **** ***** **** ********** **** *** *****. Some *** *********: ************ *** *********** **** ****** **** ******* surveillance ****** ******* *****, ************ *** ******* ********* ** *******, inabilities ** **** **** **** ***** ** ****. ***** ****** are ******* ******** **** ********, ** ****** ****** **** **** or ******* ********* ***** *** ********** *** ******* **** ******* a ***** **** ** *******. *******, **** *** **** *** systems ****** ** ******, *** ********** *** ******** **** * person ** * ********* **** ******** ** ******** ** **** do ****** ** *****.

**** *** *** ****** *** **** *********** *******, ********* *** the ******* ******** *****, *** ****** ******* ** *** ******** Face *** ******* ** ****-***** *********** ** ***** *******, ** to *** *** ************ *****.

Other **** *********** *********

******* ******** ** *** ***** ** *** **** *********** ******** space. ********* **** **********,*****,******* **** ********* ******** **** *********** ************ ** **** ** their *********. ************,******** ********* **** **** **** ********* **** *********** ************ ********.

** *** **** *** ********** ******* **** * ***** **** recognition *******, ****** ***** * ******* ********* **** **********.

Comments (15)

* ****** **** ** **** ********* *** **** ** *****. They **** *************. ** **** * *** **** ** **** to **** ******** **** ***** * *-**-* ********, *.*. ******* an ****** **** *** *** ***** ********** ******** ** **. They ***** ****** "** *** ****". ********** **** ******.

**** **** ***** ** **** ********* *** ******* ** *** office. *'* ****** *********. ** **** * *** ***** (****-****) to ***** *** ****** *** ***** *** **** ********, ****** to *********** **** ** *** *****, *****-********** *******, *** ******* 10 ******* ** ** *** ***** ******. **'* *** ******* reliably ** **** ** ******** ********* **** ****** * ******. NEC ***** ** *** ** *** **** ** *******, *.*. it ***** ****** *** ******** * ***** ****** **'* ********** sure **** ** *** ***** ******. **** **** ** ********** track ****** - **** ********* **** ********* **** ******** ** people.

*** ************* ********* *********** **** *********** ****** **** *** ** NIST **** *********** ****** ****.

*****://***.****.***/********-********/****-***********-******-****-****

*********, **** ********!

**'* *** ******* ******** ** **** ** ******** ********* **** toward * ******.

****, **** ** **** ********* *****? **'* **** ** **** people **** ******* *** ****** ** * **** *****, ************ surveillance ***********?

****, *** ***** ** *** **** ** ****** ** ****** up? *** **** * ****, **'* ****** ** *** **** results **** * ***** ********* *** * ***** ****** ** people ***** ********** *** *** ** ** * ***** ***** application **** **** ** ********* ** ********* ****** ******* ***** and ******** ** ****** ** * ********* *** **'* * lot ******.

****** *********** ******** *** ******** ******* **** *** **** *** years, ** **'* ** ******** **** ***'** **** ******* **** a **** ****** ********.

***** **** ** *********, * **** *********** **** ** *** recent "***** ** ***** **********" ****. *****://***.****.***/********-********/****-*****-**********-****

> ****, **** ** **** ********* *****? **'* **** ** make ****** **** ******* *** ****** ** * **** *****, uncontrolled ************ ***********?

*** ********** **** ***** ** ***** *** *********:

- *** * ******* **** ******** ******* ***** **** ** the ******, **** *** ****** ** ****** ** **** **. For ********, ** ******** **** (*** * **********), * ******* message (*** ********* *********), * **** ******** ** *** ************ camera (** * ****** *********** ** ***** *****), * *****-**-***-*** for * ******, **** ****** (** * ***) ***.

- *** *** ****** **** ** ** ********, * **** bell, ** ***** ****** **** * ****** **** ********* **** when *********** **** **.

> ****, *** ***** ** *** **** ** ****** ** scales **?

* *****'* ****** ** *** *** *** ****** ******* **** designed ** ***** ** ******** ** ********. ***** ********* ************* is ********* *** ***** **** ** ******* ** *** ** achieve **. **** * *********** ********** ***** ******** ******** ************ is ***** ******* ** **** (**** ****** ** *** ******* for *** *** *******). ** *** *** ********, *** **** report ** **** ****** ** ****** **** ********.

> *** **** * ****, **'* ****** ** *** **** results **** * ***** ********* *** * ***** ****** ** people ***** ********** *** *** ** ** * ***** ***** application **** **** ** ********* ** ********* ****** ******* ***** and ******** ** ****** ** * ********* *** **'* * lot ******.

***, ****'* **** *** ** **** *** ****** **** *******, e.g. *** ********, ****** **********, ***. ***** ***** ***** ***** easily *** *** ** ******* *** **** * *****-******* ******* systems *******. *'** **** ** ** ****** * ***** *** at ***** ******* ***** * **** **** ** **** *********** servers *** *********** ****** ***. (* ***'* ******* **** ******.)

********** *'* **** ***** ** *** *** ******/****** ****** * solid ***** ****** ** ***** ***** ** ***** ********** *********. Of ****** **** ** * ******** ********** ***********. * *** months *** ***** *** **** **** * ****** ** ** was **** ** ****** * ******** ******* ****** ************. **** was ***, *** ****'* *** * ****** ********** ** ****** it *** ******.

****** *** *** ********. *********** ** **** ***** *** *******.

- *** * ******* **** ******** ******* ***** **** ** the ******, **** *** ****** ** ****** ** **** **. For ********, ** ******** **** (*** * **********), * ******* message (*** ********* *********), * **** ******** ** *** ************ camera (** * ****** *********** ** ***** *****), * *****-**-***-*** for * ******, **** ****** (** * ***) ***.

* ***** ** **** * ****** *** ******* * **** heard **** ****** **** ***** ****** *** **'* ********* **** to ********** **** **** ** '**** ** *** ******' *********. It, ** ******, ******* *** *** ******* / ********* / adversary ** *** *** **** ** ************ ******** **** *** often ** **** ***** **** ** ** ***** ***** *** staring ** ** ********* *******, ******* ********, ***.

* ***** ******* **** ******** ******* **** ***** **** ****** would **** **** ****. *'* ******** * ******** ** ******** door ***** *** ****** ** ******* ** * **** ** about *.* ****** **** ******* ******** ** *** ******. ** people **** ** ***** ** **** *** ****** ****** ****** see ***** ****. ********* ******* *** ******* **, ** ***** to *** ******* ***** ***** ** **** **** *.* ******. not ****** ******** ******* ** *.* ****** ** ********* *** I ***'* *** *** ***** *** ** *** ****** ** 'look' ******** ** *** ******

****, ******, ******** ******* ***** **** ****. *** #* ********* to **** ** ********* (********* ********* **********).

*** ********* ***** ** **** **** *** ****** ** ******* lower ****** ***** ****** **** ******. * ****** ******* ****** has *** ******* ** ********* **** '****' ****** *** ****'* a ********* ***** ** **** *** **** *********** ** *** have * ******** ***** ******** ****** **** ********* ** ******* by **************.

> *** **** ** ************ ******** **** *** ***** ** such ***** **** ** ** ***** ***** *** ******* ** at ********* *******, ******* ********, ***.

***'** *****, ********* ******** ********* ** *** **** ***'* ****-***** yet *** ***'* ** *** **** **** *****. *** * think ***** *** ***** ******** ************* **** *** **** **** less-than-perfect ********, *.*. ******.

** *** ** ******* **** ** ******** ***** ****, ***** are ******* ********* ** *** ******** ******* ***** **** ** animated **** ** **** ****** *** ****. ***** *** ********* designed ** **** *** ****** ** *** **** ******** ** the ******, *** ***** ***** ******.. ****** ********* ******* ***** be ****** ****** ***** *** '******* ***********'.

** **** * ***** **** * **** ** ****..

** ******** ***** ****, ***** *** ******* ********* ** *** passport ******* *****

* ******* **** ***, ** ***** ************, *** **** *** law *** *********** ** ******* **** ***********. ***** ** ** harder ** ** **** ********** ************ **** * **** ** a ***** ** * **** ******, ***.

***** ***% **** *** ****. *** ****'* *** ********** ******* a **** *** **** ******.

**********, * ****** *** ************ *** ****** ******* **** *** Face ********* *** **** *** ** ***** ** *** ****** of **** ****, * **** ***** *** ****-**** **** *** firehouse ** ****.

******* *** ***** ** ******** ********* ** ************ ************ **** uncooperative ********. * ******* *** *** *** "****-**** ********" ** a *****-*** *********** ** **** ***** **** ** ******* */* specially ****** ******* *** ******** *** *** ** **** ** analysis ***** ******* ** *** ********* ** *** ****** *** a ******* ** *-* *******. **** **** *** ** **** there *** ** **** *********.

**** ***** ***FACIAL ************ ** *** ******** *********, *** ***'* **** ****-**** ******** ******. You ****** *** ** *** ***** ******* ** ****** *** weed **** *** *** ****** ** *** **** ** ****-****. Just **** "*" ****** *** **** *******, *** **** *** the **** ** ***** *** *** ****** *** **** *** don't **** ** **** *** **** **** ****, **** ********. Take ** *** **** ** **, * ****** ****!

**** ***** ***** ** ***** **** ****** ** ***** ***** are ********** ************ *** ********. *** **** ** **** **** in *******, **** ****** ***** ** **** ***** ** *** specially ****** **** ****** ***** ** ******* ***, ** ** a ****** ******* *** *** **** *** *** ********* ** do *** ***** **** **** ****** *** ********* *********.

*** **** *****Face ****************** **** ***** ** *** ** ***** **** **** ********? Simple ****** **** *** ***** *** ** *** ********* **** the ******** ** **** ******

  • ****** ******** **** ** ***** ***** ***** ***** ** ********
  • ****** ******** ** **** *** ****** *** *** ******** *****
  • *** ** *** **** ***** ****
  • ** ****/*******/*******
  • ************* - ***** *** ****** *** * ********
  • ***** ******* ** *** **** *** ***** *****, ***** **** high **********

**** * *** ** **** **** *********, **** **** **** you **** ** *** **** ** ********.

**** ******.

**** * *** ** **** **** *********, **** **** **** you **** ** *** **** ** ********.

*** ********* ********* **** ****, **** ******* **** *********** ** deep ********, **** **** **'* ****** ** **** **** ** cameras ***'* *** * ***** ****. *** / ** ** wear * *** ** **********, ***. ** **** *** **** a ******** ********** ** ****** **** ***.

** ******, ** *** ********* **** ***********, *********** ************** ******* would ***** **** ****** ********. **** *****, ******.

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports

AI Startup Anyvision Raises $28 Million Led By Bosch on Jul 20, 2018
Anyvision is the most ambitious heavy-spending video surveillance startup in many years. And, now, the startup has raised $28 million led by...
Directory of Video Surveillance Startups on Jul 18, 2018
This directory provides a list of video surveillance startups to help you see and research what companies are new or not yet broadly known entity...
FST Fails on Jul 17, 2018
FST was one of the hottest startups of the decade, selected as the best new product at ISC West 2011 and backed with tens of millions in...
Hikvision Wins Chinese Government Forced Facial Recognition Project Across 967 Mosques on Jul 16, 2018
Hikvision has won a Chinese government tender which requires that facial recognition cameras be set up at the entrance of every single mosque...
Axis Perimeter Defender Video Analytics Tested on Jul 12, 2018
Axis 'high security' video analytics offering is Perimeter Defender, OEMed / developed with Digital Barriers. But how good is Perimeter Defender?...
Belgium Bans Private Facial Surveillance on Jul 06, 2018
Belgium has effectively banned the use of facial recognition and other biometrics-based video analytics in surveillance cameras for private,...
Axis Guard Suite Video Analytics Tested on Jun 25, 2018
In 2015, we declared Axis' Guard Suite analytics "weak", with missed detections and false alerts common. But after nearly 3 years and a 2.0 version...
Huawei Software Defined Cameras on Jun 25, 2018
Huawei is aiming to break the reputation of Chinese companies not being good at software. The company is now leading their video surveillance...
GDPR / ICO Complaint Filed Against IFSEC Show Facial Recognition on Jun 20, 2018
IPVM has filed a complaint against IFSEC’s parent company UBM based on our concern that the conference violates core GDPR principles on...
IFSEC 2018 Final Show Report on Jun 20, 2018
IPVM attended the IFSEC show for the first time this year. The Chinese took over the show, centered on Hikvision, flanked by Dahua, Huawei and a...

Most Recent Industry Reports

AI Startup Anyvision Raises $28 Million Led By Bosch on Jul 20, 2018
Anyvision is the most ambitious heavy-spending video surveillance startup in many years. And, now, the startup has raised $28 million led by...
Fail: Dahua "Didn't Check The Lux Levels but It Was Dark" on Jul 20, 2018
Dahua UK has been promoting their camera quality on LinkedIn: I, and others, asked what the lux level of the scene was. (background: Lux Rating...
Free 100+ Manufacturer-Customized Camera Calculator Released on Jul 19, 2018
Now, any manufacturer has a customized IPVM Camera Calculator, free. The goal is to make it easier for companies to help their customers better...
Improved Security And Surveillance Bidding - 2018 MasterFormat Divisions Examined) on Jul 19, 2018
Navigating the world of system specifications and bidding work can be complex and confusing, but a standard format exists, and understanding it...
Last Chance - Security Sales Course Summer 2018 on Jul 19, 2018
Today is the last day to register. Based on member's interest, IPVM is offering a security sales course this summer. Register Now - IPVM Security...
Directory of Video Surveillance Startups on Jul 18, 2018
This directory provides a list of video surveillance startups to help you see and research what companies are new or not yet broadly known entity...
Ladder Lockdown and Ladder Levelizer Tested on Jul 18, 2018
Ladders are a daily necessity for surveillance and security installers, but working on an unstable surface can be extremely dangerous. In addition...
FST Fails on Jul 17, 2018
FST was one of the hottest startups of the decade, selected as the best new product at ISC West 2011 and backed with tens of millions in...
Axis ~$100 Camera Tested on Jul 17, 2018
Axis has released their lowest cost camera ever, the Companion Eye Mini L, setting their sights on a market dominated by Hikvision and Dahua. Can...
Amazon Ring Alarm System Tested on Jul 16, 2018
Amazon Ring is going to hurt traditional dealers, and especially ADT, new IPVM test results of Ring's Alarm system underscore. IPVM found that...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact