Axxon Face Search Tested

By: Rob Kilpatrick, Published on Oct 26, 2018

AxxonSoft has brought facial recognition to their Axxon Next VMS for free with the simply named Face Search, claiming to allow users to find subjects across multiple cameras to drastically cut search time.

ipvm tested 2

In this report, we provide our full test results on Axxon's Face Search, examining:

  • How many false negatives or positives to expect?
  • How well does the analytic handle subjects looking down or away from the camera?
  • How does recognition perform in low light, <1 lux with IR, and WDR scenes?
  • How does Face Detection impact CPU usage?

Readers interested in facial recognition should also see our recent test of Dahua's Face Recognition Camera, the HF8242FN-FR.

************ ******* ****** *********** to ********** **** ****** **** **** *** simply ********* ******, ******** ** ***** users ** **** ******** across ******** ******* ** drastically *** ****** ****.

ipvm tested 2

** **** ******, ** provide *** **** **** results ** *****'* **** Search, *********:

  • *** **** ***** ********* or ********* ** ******?
  • *** **** **** *** analytic ****** ******** ******* down ** **** **** the ******?
  • *** **** *********** ******* in *** *****, with **, *** *** scenes?
  • *** **** **** ********* impact *** *****?

******* ********** ** ****** recognition ****** **** ****** ****** **** ** Dahua's **** *********** ******, the ********-**.

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

Summary: ******** ****** ***** ******* ** ****** ******** 

***** ** *** *****, Axxon ****'* **** ****** worked ****** **** ** default **% ********** ********, with **** ******** ******** matched, **** *** ****** face ********** **** * week ** ******* ** a ***** ****** ** ~30-40 ******. ***** **** Search *********** **** **** time ******** ** **** specific ******** ****** ******** cameras.

************, ********* ********** ****** in ***** ***** *** WDR ********** **** ***** face *** ************ ** past ***** (*** *** test *******'* **** *** ******), **** ***** ***** usably ********** ** * <1 *** *****.

Some ******* **** *** *********

*******, ***** *** ******* key ****** ** ** aware **:

  • **** ***************:**** ******** **** ********** mistaken *** ****** ** Axxon's **** ******, ** high (>**%) ********** *******. This **** ***** ******** with ******* *** ** our *****. ***** ***** similarity ********** (~**-**%) ******** more **********, ** ****, but ***** ****** *** below *****'* ******* (**%).
  • ******* ***** ****** **********:** *** *****, **** other **** *** *********, face ****** ********** ********* by ~**% ** **** when ******** ****** **** or **** **** *** camera, ************ ******* ******* missed ******** (~*-**% ** the ****).
  • ***/*** ***** ********** **********:************, ********** *** ******* by ~**-**% ** *** light (~*.* *** - 2 ***), ***, ** when ***** ********** **, similar ** ***** ********* in **** *****.

Upcoming **** **** *** *********

***** ***** ****'* ****** recognition ** ******* ** forensic *** ** ******* versions, ********* *** ***** to ******* **** ********* in *** **** *** months. **** ****** ** early ******* ** ***** analytics *** ***** *********** fairly ******* ** **** Search, *** ** ** unknown **** *******/************ **** be ** ***** ********** versions. ** **** ** retest **** ******** *********.

*******/************

**** ****** ** ******** at ** ********** **** with ***** **** ******** licenses (~$*** ****/*******) *** as ** ***-** ******* when ***** ***** **** Professional. ***** **** ***** does *** ******* **** Search. ****** **** **** recognition ********* **** ******* additional *********.

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

**** ****** ** ****** to ***, **** ***** selecting *** ** **** cameras, ********* * ********* image ** *** *******, and ********* ********** ********* (if *********). ********** ******** to **%, ***** ** found ********** ******** ** our *****, **** *** mistaken ************ ** ******** aside **** *-* ********, discussed *****.

*** ***** ***** ************ how ** *** *** Axxon **** ****** *******.

Configuration ********

**** ****** ******** **** detection ** ** ******* for **** ******, ***** essentially **** ******** *** rule ** ** *****, analysis ********** *** **** width/height ******** ** *********, and ********* *******.

**** **** ******** ********** may ******* ****** *** usage ** ******* ***** 1080p. *-*** ****** ** our ***** ****** *********** CPU ******, ********* ******* below ** **** ******.

*** ********* ***** ***** you ******* ************* ** face ********* ** ** individual ******.

Solid ****** *********** ***** ******* ** ****** **********

***** *****'* ******* **% similarity ** ******, **** subjects **** ******** **********. For *******, *** ******* below *** ************ ********** with >**% ********** ****** multiple ******* ** ******** conditions *** ** ******** angles, **** ** ***************** at ***** ********.

most subjects recognized with high similarity

Bearded *** *************

*******, ******* ******** **** frequently ********** ** **** other ** * **** similarity *****. *** *******, the ******* ***** ** recognized *** **** ** himself ** **% **********, but ** ******* ******* man ** *** **** level. ******* ******* **** seen **** ***** ******* men ****** *******. **** that ** ***** ****** features **** ** ******* or **** ****** ***************** in *** *****.

bearded subject

Lower ********** **** ***** ******

*** ******* ****** ** Face ****** ********** *** head ****. *** *******, when ******** ****** **** or ** *** **** (as **** ** **** walking ********), ********** ******* by ~**-**% ** ****. However, ****** *** ****** test ** *****'* **** Rec ******, **** ****** caused ******** ****** ****** detections, ********* in * **** ** testing.

head titled 2

<1 *** ********* ********, *** ******* ******* **********

***** ******** *** ********** faces ** ~*.** ***, although ********** *** ******* by ~**-**%. **** ** also ** ******** ** the ***** ******, ***** failed ** ******/********* ******** at

low light 2

CPU **** ******

*****'* **** ********* ********* increased **** ** ~*-*% per ***** ****** ***** analyzed ** *** *****, using ** ***** ** 5557U *********. **** ******** in ~**% ***** *** usage *** **** ***** cameras, * *********** ******** over ******* *** ******* Face *********, ***** ******** only *-*% ****.

*******, *** ***** ****** extreme **** ******* ***** 1080p **** ********. ****** two **** ***** ** view *******, * *** 5 **, ********* *** usage ** **-**%****, ********* ** **%+ CPU ***** *****. ***** using ****** ********** ******* or ***** **** **** motion ***** ****** ****** of ***** *********. ***** resolution ******* *** ** analyzed, ****** **** ********* range *************** *********.

CPU ****/*** ******* *******

*********, ***** ********* **** detection *** *********** **** on *** ******'* ***. However, **** ***** **** they **** ** ********* Intel's ******** ******** ****** toolkit ** *** **** future ** ******** **********, with ***** ******* *** GPUs.

Wide ***** ** **** / *** *** *** **********

**** **** ***** **** Search *** ** *** on *** ****** **** Face ********* *******, ***** with **** ****** ** view ****** *** *** provide *** ********* ******* in *** *****, *.*., in *** ***** ** view *****.

wide field of view

***** ********* ************ ** 50 ****** ******* *** eyes *** *********, ** roughly ***-*** ***. ************, even ** *** ****** are **** ****** *** analysis, ***** ****** ****** of *** *** ****** of ***** ***** *******, as ***** ****** ****** levels *** ***** *** usage ******.

Versions ****

*** ********* ******** **** used ****** *******:

  • ***** ****: *.*.*.*.****

Comments (13)

"**** ****** ** ******** at ** ********** **** with ***** **** ********"

*** *** **** ***** this? *********** * **** is **** ** ** included ** ***** ******** version (**** ********* *******), is ******** ** ***** Professional (** ** ***** cost ****** **** ********** in **** ** ********) and *** ********* ** the ***** ********* ***** version.

** ** ********* *** "free" ** *** **** to ** ** *** most ********* ******* ** this ** *** ******* feature *** ****. * guess ** ***** ** "free" ** *** ******* needed *** ******** ******* for **** ***** ******** and *** **** ******** automatically.

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

**** ****** ******* ********** as **** ** ** pack ***** *** ******** some **** *** *** includes ******** **** ******* tracking **** **************, ******** search ** ******, ****** type **** *****/*******, ***** and ***. **** ****** as * **** ** our ** **** ** free ** ******** *** optional ** ************ *******.

***** ****, **** *** usage *******!

*-*% *** ***** ** not ***, ********, *********** that ** **** **** to ********** ******. 

**** ** *** ******** calculator ** ****** ******** according ****** ** ******** and ********* **: *****://****.*********.***/****/**********.***

*** ****, **** *** 20 ******* ** **** 1Mpix *** **** ******** server.

**, *** *********** ** currently * ***** ***** to *** **** ********** for *** *** *******, while ** **** ** available **** ******* **** and ******* ** ** pack **** *** *** analytics, **** ****** *******, LPR *** ** **.

*** *** ****, **** there *** **** ************ (software *** ********) ****** very **** ** ******* CPU *********** ************.

** **** **** ** decompress ******.

***** **** * ******, and **** *****. 

*** *** ** **, but ******* ***** ************* in **** ****. *** best *********** ** **** best **** ********, ** minimal *********** ** *-** FPS.

** *** ****** ***** Representative *** ***** ** the **, ** **** had ******** ******** *** response **** *** ******* on **** ***** **********. The **** ********* *** recognition ********** ** ****** to ****. ** **** recently ******** **** ********** in ****** ******* ******** environments *** *** ********* excellent ******** **** *** partners ****** *** *******. The ********** ** ********* being **** ** ***** K12 ************ ** **** as **** ***** ***** deployments.

** ** ******** ** install *** ******* ******** to ******* **** ******** technology. **** ***** ********* we **** ***** ********** accuracy. ** *** **** the **** **** *** Live **** ****** ******* including *** / ****** classification *** ** *** having ********** ******* *** are ******* ******* ** partnering **** ***** ** release **** ******* ** security *********.

***** ****** ********* ** this ******* *** * great ********* ** *** the ********** ***** *** the ******* ** *** it **. ***** ** the **** **** ** a ***** ****** **** detailed **** *******.

******'* ***** **** **** Mr. *****.

***** *** ************ ** AxxonSoft ** ****** *** Cyprus, ** **** *** the ****** ** ****** many ** *** *********** partners/resellers ** *******-** **** advanced ******* -***** ******- with ***** ******* *** enthusiastic ****** **** *** end-customers *** *** ******** managers *** **** **. Hotel *********, ******** *********** in ********* *** ***** large-scale ************** **** *****, shipping *********, **** *****, military **********, ** **** some ********.

***** ** *** ** use *** ***** ******* (140dB *** ** ******* and ********* **** ***** Starlight *.*******@******) ** ******** almost *** ******* **********. With *** ********* ***** on *** ******* ******** (for *** ***** ** be **********) *** *** minimum ********** ******** ** do ****, ** ********* the *********** ******** *** the ******* (********* ******** a **** ***** **** to ** **: *****://****.*********.***/****/**********.***). *** results *** *******.

**** *
*************** ** *** **** team *** *** **** very ******** ****. ********* work, **** ****.

**** *
********* *** ******* *** misidentification, ** *** ****'* refer **** ***** *** men *** *** ****** the **** ****** (******** at * ********* ***** in ****, **** * longer *****, **** * different ***** *** ****** within *** ******** ******** etc.), * ******'* ** absolutely **** ****** **** the ***** ****** ** a ********* ***. ** my *******, ** **** close **** **********, ** I **** * ******** manager ********* *** * suspect, * ***** ****** like ** **** ** opinion ** ** *** and *** *** *** algorithm ******.

@*********** ************ #*
**** ******* **indeed ******** ** ***** **** ************ ******* as ** ***** **** *** ****** ****** ("Extra Feature Package"). With this feature you can search for a face in a camera. And indeed can't be included in the Start Version.
*** ***, **** ******* is ** ******* ******** in ***** **** ******** Version **** ** ********** cost,but also ** * "*****-****** **** ******", which means that you can search for a face in many (** ***) ******* ************** and also have the exact spots (where the faces are recognized/found) pinpointed on a 3D map. This feature is extremely helpful for the operators.

***** * ****** *** had * **** ***** in *** ********* ****, but **** ****** ** completely, *** ** ********** at ***, ***** **-***** the ***?  

********, ********** **** ** below **%, *** **********, even ******, ** **** be *****.

* **** ** **** for * ************ **** placed * ****** ***** light *** ** ***** dome ******* **** ******* every ****** ** **. It *** **** ****** to ******* ******'* ********* and **** **** **** up ** *** ****, but *** ** ****** or **** **** ** was **********. 

**** ****, ***** *** for **** ******** ****.

 

*** ********* **** ********** between *** **** **** a ***** *** * new **** *** **. Thank *** *** ****. I ***** **** *** reason ** **** ** do *** **** ****** number ** *** **** a ***** ** *** training *** *** **** recognition *********. ** *** every **** ******** ********* it *** ** ***** easily - ** *** going ** *** **** appropriate ****** **** *** training ***.

 

** ******** *** *********** we *** ***** ** use ***** ******** ******* that ******** ****** ********* implementation ** **** ******** inference ******. * **** it **** *** ** to ******* **** ******** on *** **** ******.

****** ** *** **** team, **** ********* *******! The ****** **** ******* of ***** **** *** four ********, ***** ******** all *** *** ******** listed, *** ** ********** from *** ********* *******. It **** ** ****** be ***** **** ******* that ***** **** ** a ****** ****** *********** and ********* ** **** choose *** ******** ******** with *** *********** ********** where ** **** *** necessary *************** *** **** servers *** *******. **** ** the **** ** *** hardware **********: 

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

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

The HIVIDEO $31 Face Detection DVR Tested on Apr 25, 2019
Face detection in a $31 DVR? That is what "HIVIDEO" (not to be confused with Hikvision, even if the company intends to do that) was promoting at...
Verkada Video Quality Problems Tested on May 23, 2019
Verkada suffers from numerous video quality problems, not found in commercial IP cameras, new IPVM testing of Verkada vs Axis and Hikvision...
Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...
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 Dual Lens Face Recognition Camera Tested on Nov 19, 2019
Hikvision's Dual Lens Facial Recognition camera, claims that it "adopts advanced deep learning algorithm and powerful GPU to realize instant face...
Avigilon Appearance Search Tested on Oct 30, 2019
Avigilon Appearance Search claims that it "sorts through hours of video with ease, to quickly locate a specific person or vehicle of interest...
Rhombus Cameras, VMS and Analytics Tested on Nov 06, 2019
Rhombus boasts they have created "the new standard in Enterprise, cloud-managed video security" and told IPVM in January 2019 they offer twice the...
BriefCam Video Analytics Tested on Jan 06, 2020
BriefCam, acquired by Canon in 2018, is one of the most commonly used video analytics offerings in the West. But how well does it work? We...
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...
Bosch / Milestone Forensic Search Tested on Jan 08, 2020
Bosch's Forensic Search Milestone plugin integrates Bosch IVA and EVA analytics search in Milestone XProtect, claiming to "gain complete control on...

Most Recent Industry Reports

Motorola / Avigilon Drops ISC West on Feb 26, 2020
Motorola Solutions has pulled out of ISC West 2020 effective immediately, because of coronavirus concerns, IPVM has learned. This is done amidst...
Cancel or Not? Industry Split Over ISC West on Feb 26, 2020
The industry is split, polarized, over whether ISC West 2020 should run or be canceled. New IPVM survey results of 400+ respondents show heated...
Coronavirus Hits Sony, Bosch Says Switch on Feb 26, 2020
Sony's fall in video surveillance has been severe over the past decade. Now, they may be done. In this note, we examine Bosch's new...
Video Surveillance Cameras 101 on Feb 25, 2020
Cameras come in many shapes, sizes and specifications. This 101 examines the basics of cameras and features used in 2020. In this report, we...
Favorite Video Analytic Manufacturers 2020 on Feb 25, 2020
Video analytics is now as hot as ever, driven by the excitement of advancing deep learning offers. But what are actually integrator's...
Latest London Police Facial Recognition Suffers Serious Issues on Feb 24, 2020
On February 20, IPVM visited another live face rec deployment by London police, but this time the system was thwarted by technical problems and...
Masks Cause Major Facial Recognition Problems 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...
Every VMS Will Become a VSaaS on Feb 21, 2020
VMS is ending. Soon every VMS will be a VSaaS. Competitive dynamics will be redrawn. What does this mean? VMS Historically...
Video Surveillance 101 Course - Last Chance on Feb 20, 2020
This is the last chance to join IPVM's first Video Surveillance 101 course, designed to help those new to the industry to quickly understand the...
Vulnerability Directory For Access Credentials on Feb 20, 2020
Knowing which access credentials are insecure can be difficult to see, especially because most look and feel the same. Even insecure 125 kHz...