Masks Cause Major Facial Recognition Problems

By: Rob Kilpatrick, Published on Feb 24, 2020

Coronavirus is spurring an increase in the use of medical masks, which new IPVM test results show cause major problems for facial recognition systems.

IPVM tested four facial recognition systems to see how they performed with masks:

The 1-minute video below overviews our findings:

*********** ** ******** ** increase ** *** *** of ******* *****, ***** new **** **** ******* show ***** ***** ******** for ****** *********** *******.

**** ****** **** ****** recognition ******* ** *** how **** ********* **** masks:

*** *-****** ***** ***** overviews *** ********:

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

Masks *********** ****** *********** ***********

** *** *****, ****** recognition ********** ******* ************ (over ** ****** **********) when ******* ****-***** **** masks, **** ******** *** recognized ** *** ** most *****, *** ** faces **** ******** **** of *** ****.

************'* ********** ********* **** ** ************ recognize ********, *** **** required ********** ** ** decreased **** **** ** medium ** ***. ***** recognition *** ********, ** is ******* **** **** will ****** ** ***** identifications ** ***** *********** with ******** ** ********* of ********.

Further ******** ********

** ** ******** **** these ************* ***** ******* masked **** *********** **** further ******** ** ***** algorithms. *******, *************, ********* will **** **** ***** points ** **** *********** on ** ** **** of *** **** ** covered, ****** *********** *********, even **** ********.

Drastically ******* **********

***** *****, **** ******** to *** **** ******* not ******* * ****, confidence ******* ** **** 60 ****** **** ******* a ******* ****, **** nearly ***% ********** ** just **** **% ** the********* **** **** **** rec ******.

** ***** ** ********* a **** ** ***** levels, ******* ********** ****** to ** ******* ** ~25%. *******, *********** ******** inconsistent ** **** *******, with **** ******** ********, but *** **********. **** was ********** ****** **** hair ******* *** *******'* forehead, ****** ** **** difficult ** ****** *** face.

**************** *********, **** *********** reduced ********** *** ******** total ******, **** **** using *** ********** ***** requirements. *** *******, *** face ***** ******* **** only **-** **********, ******* of **-** **** *** same ******* *** *** wearing * ****.

Avigilon **** *********** **** ******** *** **** ******/*** **********

** *** *****,********'* ****** ************** *** **** *********** rates, *********** *** ******** walking ******* *** ***** when ***** ****** ** low ********** ******** (******** does *** **** ***** confidence ******).

*******, **** **** ***** recognition ****** ** *** tests ***** * ***** population, ***** ****** *** assume ** ***** ******** similarly ** ****** ************* where *********** *** **** diverse. ** ** ******* that ***** ************ *** missed ************ **** ******** as *** ****** ** subjects ********* ******* **** more ****** **** ** more *********** *** ****** to **** ** ****** to *** ****** ** looking **********.

No ***** ******** ** *****: *******

** *** *****,******* ****** ********************* ****** ***** ** people ******* ******* *** scene **** ******* *****. These ********'* ***** **** not ******** ** *** and *** ********** **** Verkada's **** ****.

All ******* *** **** **********

*** ******* ****** **** miss ****** ********** - meaning **** *** ****** did *** **** ********* a **** *** *******, which ** ********* ** even *** ** ********** what ******'* **** ** is:

  • ******** ****** ****** ***** walking ******* *** *****.
  • ********* *** *** ****** best *********** **** *** at *** **** ** a ***** ********** ********* of **. *** ******* higher ********* *** *********** misses.
  • ******* ****** ****** ********** and ****** ******** ***** in *** *****.
  • ******* *** *** ********* anyone ** *** ***** wearing * ******* ****.

Improvements ** ****** ********* **** ***** *******

********* * **** **** a **** ** * solvable *******. *** ***** is **** ******* ****** did *** ***** ***** systems ** ********* ***** with *****. **** *** be ****** ** ****** new ******** **** ** faces **** ***** **. As ****, ** ***** expect ****** ******** ******** from **** ******* ** include ****.

Harder ********* ** ********* ***** **** *****

***** ********* *********** ****** go **, *********** *********** faces *********** ******. ***** hide *** ****, ****, mouth, ****, *** ***, essentially ************ ******* ** match ** **** *** forehead.

****** ** ********* ***** can ***** *** ** be **** *** **** sometimes ** ***** ** correct *** ************* *** accuracy, ********** **** ****** scale, **** ** *** reduced.

*** ****-**** ******** **, structurally, ******** ****** ******* where ******* ***********, ****-********** lighting, *** ****** ********** their ***** ********* *** odds ** ********. *** example,*****'* ******* ********** ** already ********** ** **, ** their ********* ***** ***** demonstrates:

*** **** ** ******** works *** *** **** mistakes *** **** ** not *********. *******, ****** control *** **** ** tuned ** ***** **** matches / ****** ** the ********** ** **** that ** ** ****** to *** ****** ** quickly **** ***** ***** users **** ********.

** ********, ****** *********** in ***** ************, *.*., the ***-***** ***** **** examples *** ***** ** face *** ****** ******** - ********, **** *******, wide *****, ***., **** combined **** **** ***** are ****** ** **** facial *********** ******** *** norm, **** **** *************.

Comments (10)

*** *******, *** **** below ******* **** **** 30-40 **********, ******* ** 60-70 **** *** **** subject *** *** ******* a ****.

* ** *** **** I ***** ********* ***** anymore **** ** ******* a **** :)

****** *** ******* ***** recognize ******** ***** **** masks.

*** *** ********* ****** there *** ** *********** that ****** *********** ***** work **** **** *****?

** *** ********* ****** that ********* *** ******* were ******** **** ** we *** * **** test ** ******.

***, ***** *** ****** on **** **** *** can ***** *** **** think ** **** **** but ** *** **** actual ******* ** **** what *******.

* ******* *** ***** were **** **** *** same **********?

***, **** **** *** done **** ***** ******* (that *** *** **** resolution ********* *** ******** and *******), ****** ** also **** ** *** Avigilon *** *******, *** only ********** ******* ***** and ** **** ***** masks *** *** ******** detected.

*********, ******** **** ***-******* the *******, (*** *******) will ******* *** ****** recognition. **** ** ************ noted ** * ****** Insane ***** ***** ****. (Seriously)

********** *** ****** *********** can **** **** **** masks **, *** **** how **** ** **.

******, #*, ***** **** reports ******* ******** ****** our **** *** *********, which ** ***** ** the **** *****.

*** ******* ** **** accuracy ** ***** ** decline ********** ** **** optimization ** *********, ** these ******* ****.

** **** ***** ************* need ** ***** ** how **** ** *****, at *****, ** *** wild, ***., *** **** that ** *** ************* work.

*********, * ******* ******* called ************ ** **** ************ ********** ** ** 95% ******** **** *** with *****. **** **** claim **** *** ******** everyone ** * ***** of ** ** ** (masked) ****** “****** * second”. ****** **********.

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/Smart Camera Tutorial on Feb 20, 2020
Cameras with video analytics, sometimes called 'Smart' camera or 'AI' cameras, etc. are one of the most promising growth areas of video...
IronYun AI Analytics Tested on Feb 17, 2020
Taiwan / US startup IronYun has raised tens of millions for its "mission to be the leading Artificial Intelligence, big data video software as a...
Monitoreal "Completely Autonomous" Home AI Tested on Feb 12, 2020
Monitoreal claims to allow users to "see the things you want (people, vehicles, animals) and ignore the things you don’t”, using AI to distinguish...
Avigilon Facial Recognition 'Appearance Alerts' Tested on Dec 18, 2019
Avigilon has released 'Appearance Alerts' in ACC 7.4, which adds real-time facial recognition. To see how this performed, we tested them with...
Hikvision Acusense Analytics Tested on Sep 23, 2019
Hikvision touts "The Magic Behind It All" in their new Acusense line are 'deep learning algorithms' inside these cameras and recorders. But how...
Axis Perimeter Defender Improves, Yet Worse Than Dahua and Wyze on Sep 19, 2019
While Axis Perimeter Defender analytics improved from our 2018 testing, the market has improved much faster, with much less expensive offerings...
Vivotek "Neural Network-Powered Detection Engine" Analytics Tested on Sep 17, 2019
Vivotek has released "a neural network-powered detection engine", named Smart Motion Detection, claiming that "swaying vegetation, vehicles passing...
Verkada People And Face Analytics Tested on Aug 16, 2019
This week, Verkada released "People Analytics", including face analytics that they describe is a "game-changing feature" that "pushes the...
Hikvision DeepinMind 2019 Test on Jun 06, 2019
In 2018, Hikvision's DeepinMind AI NVR performed terribly, recognizing vehicles, animals, and other objects as humans, misclassifying demographics,...
Hikvision DeepinView Camera Analytics Tested on May 08, 2019
Hikvision is expanding its 'deep learning' offerings with a new camera series called 'DeepinView' claiming false alarm reduction and improved...

Most Recent Industry Reports

YCombinator AI Startup Visual One Tested on Apr 02, 2020
Startup Visual One, backed by Silicon Valley's powerful Y Combinator, aims to be "Your 24/7 Watchman" with advanced analytics and object...
Free IPVM Memberships For The Unemployed on Apr 02, 2020
IPVM is giving 3-month free memberships (regular price $99) for the unemployed, no questions asked. To get it, just contact us, your request...
Dahua Faked Coronavirus Camera Marketing on Apr 01, 2020
Dahua has conducted a coronavirus camera global marketing campaign centered around a faked detection. Now, Dahua has expanded this to the USA,...
Video Surveillance Trends 101 on Apr 01, 2020
This report examines major industry factors and how they could impact video surveillance in the next 5 - 10 years. This is part of our Video...
USA's Seek Scan Thermal Temperature System Examined on Apr 01, 2020
This US company, Seek, located down the road from FLIR and founded by former FLIR employees is offering a thermal temperature system for the...
Terrible Convergint Coronavirus Thermal Camera Recommendation on Apr 01, 2020
A week after Convergint disclosed falling revenue, pay and job cuts, Convergint is touting 'extensive research' that is either grossly incompetent...
The IPVM New Products Online Show April 2020 Opens With 40+ Manufacturers on Mar 31, 2020
IPVM is excited to announce the first New Products Online show, with 40+ manufacturers, to be held April 14 to the 16th, free to IPVM members,...
USA's Feevr Thermal Temperature System Examined on Mar 31, 2020
This US company has burst on to the scene, brashly naming itself 'feevr' and branding itself as a "COVID 19 - AI BASED NON CONTACT THERMAL...
JCI Coronavirus Cuts on Mar 31, 2020
JCI has made coronavirus cuts, the company told employees in an email that IPVM has reviewed. Inside this note, we examine the cuts made, the...
Add Door Operators To Fight Coronavirus on Mar 31, 2020
IPVM recommends that integrators advocate and end-users consider adding door operators to fight the spread of coronavirus. This delivers...