Facial Detection Tested

By: IPVM Team, Published on Nov 16, 2018

Facial detection and recognition are increasingly offered by video surveillance manufacturers.

Facial detection detects faces in an image/video but not whose face it is. However, even facial recognition (where the system attempts to determine the identity of each face) depends on facial detection first. That is, the system cannot attempt to recognize a face until it detects that an object is a face. As such, facial detection is a pre-requisite for facial recognition systems.

facial detection test

3 fundamental approaches exist to performing facial detection:

  • HAAR Cascades
  • HOG
  • CNN / Deep Learning

Performance varies on 3 fundamental metrics:

  • Accuracy of detecting faces - while it is 'easy' to detect a face looking directly at the camera in a well-lit scene, performance can vary significantly depending on how a person tilts their head (down, left, right, etc.) and the lighting conditions of the scene (shadows, darkness, noise, etc.).
  • Computing load to detect faces - Finding and determining what objects are in a scene and whether those objects are a face (instead of a tree, a car, a cat, a bowling ball, etc.) can be very computationally intensive while many video surveillance devices (e.g., IP cameras, NVRs) have significant constraints of processing power
  • Chip / hardware used - Intel (i5/i7, Movidius 2 & X, FPGA); Nvidia GPUs, etc.

This is the first of a new series of machine learning / video analytic testing that IPVM will be doing.

****** ********* *** *********** are ************ ******* ** video ************ *************.

****** ********* ******* ***** in ** *****/***** *** not ***** **** ** is. *******, **** ****** recognition (***** *** ****** attempts ** ********* *** identity ** **** ****) depends ** ****** ********* first. **** **, *** system ****** ******* ** recognize * **** ***** it ******* **** ** object ** * ****. As ****, ****** ********* is * ***-********* *** facial *********** *******.

facial detection test

* *********** ********** ***** to ********** ****** *********:

  • **** ********
  • ***
  • *** / **** ********

*********** ****** ** * fundamental *******:

  • ******** ** ********* ***** - ***** ** ** 'easy' ** ****** * face ******* ******** ** the ****** ** * well-lit *****, *********** *** vary ************* ********* ** how * ****** ***** their **** (****, ****, right, ***.) *** *** lighting ********** ** *** scene (*******, ********, *****, etc.).
  • ********* **** ** ****** faces - ******* *** determining **** ******* *** in * ***** *** whether ***** ******* *** a **** (******* ** a ****, * ***, a ***, * ******* ball, ***.) *** ** very *************** ********* ***** many ***** ************ ******* (e.g., ** *******, ****) have *********** *********** ** processing *****
  • **** / ******** **** - ***** (**/**, ******** 2 & *, ****); Nvidia ****, ***.

**** ** *** ***** of * *** ****** of ******* ******** / video ******** ******* **** IPVM **** ** *****.

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

****** **** ****, ** test ***, **** *** CNN ********** ** ****** detection *********** ***** *********** (FPS) *** ********* ***** required ** ***** **-*****. In ******* *******, ** will **** ** ******** Myriad2, *******, *** ****** GPUs, ** **** ** add ******** ***** (******* Precision). *** **** *** this ******** ** ******.

Facial ********* ********** ********

*** ***** ** *** not ******** **** ***, HAAR *** ***, *** 8-minute ***** ***** ********* each *** ******** *** tradeoffs ***** ****:

Code / ******* *** ****

*** **** *** ******* used *** *** **** is ****** ******'* ****** **** ********* test ********** ** ******.

** ******:

  • **** ***, ***
  • ****** ****
  • ******** ****-*********-******-****

** **********, *** ***** interested ** *** **************, see ********* ****** ****, ********* ***** *** context:

Test ******* *** ****** *********

***** **** ************ *** far **** ********* ********* than *** *** ****, in *** ****, ***** the **** ***** **-***** for *** * **********, the ******** *** ****** detection ***** ********* ******* frames *** ****** (~*****) as *** **** **** accurate **** ********** ***** delivering ***** *** *** of *** **** ****** accuracy ** ****. *** video ***** ********* ***** results:

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

  • ***** ******** ********** *** ********* *** ** ****** on ***********. ******** ********* model *** ************* **** data-type ********* ********** (****->****) and***** ********* ****; (*) ********** *** model ** *** ****** hardware (**/**/**, ********, ****). This ******** **** * smaller ************ **********+***) ********* better **** ************ ******** results.
  • *******, ~***** *** ** entire ***** **-***** **** still ******** ********** *** video ************ ************. **** chips *** *** *** inside ** ******* (*** to **** *** ***** constraints) *** ***** **** may ** *** ** recorders, ********* ***** **** to ******* *** **** than ***** ** ****** 8, ** ** **** cameras ********* ***** ******** to * ********. ******** IPVM ***** **** ***** Intel's ******** ***** (** particular *** ******* *** MyriadX) ***** *****'* ****** Compute ***** (***) *** NCS2 (***** *** *******).

********

**** *** *** ******* overall ********* ************ ********** struggling **** ****** ***** as ***** ** *** clip *****:

*** ********* ******** ***** but ******** **** **** 'flickering' ** *** **** was *********** **** *** then **-******** ** ***** below:

** ********, *** *** detected ***** ***** ******** without *** ********** ** HOG, ** ***** *****:

Questions / ******** / ***********

**** ** *** ***** test ** **** *** series *** ** *** presenting *********** ******* ** show **** ** *** working ** *** ** encourage *** ** *** questions *** **** *********** for ********* ******, ******, hardware, ***. ** ****.

Comments (10)

* **** ** ******* *** ********** *******. ***** *** ******** ******* ** ******* ********. *** ***** ******* ** ***** **** ** **** ****, I'd ********* *** ** ****** ** *** **+ ********.

***** ******* ** ****** ** ******* ******* *** ** *** expanded **** ***** ***** ** ***** ************ ******* ******* ******** approaches.

**** ** ** * **** ** *** *****-******** ****** ******* ***** *(***** **** *** ******* **** ****, *.*.,******** **** ** ***** ** ***** ******** ** *******).

** *** **** ******* ** ******** ** **** ******** ************* better ********** ******* ******** ************ ** **** ***** ** ***** surveillance.

*****, *** ********* ** *********** *** ******* / *****, ****** ask.

**** **** ******* ******* ** ********* *** ******* ****. *** police ** ***** ***** ** *** ** *** **** ***** on ****** *********** ** ****-****** ******, *** **** *****'* ******** my **** ***.

**** **** **** *** * *** **** ******** ***** ** (you *** *** ** ** *** **** ** `--****** ********`). The *** ** ** ***** *****, *** ** ** *** more ****** **********/********* *********. ** *** **** **** *********, ** will *** **** *** ** *******. ** *** **** ** to *** ******* ***-******* (*** ** **** ***), ***'** **** to******* **** **** ******. * ***** **** **** *** ******* ***:

- **: ******** *** ** **** * ******'* **** ****** the *******. **, *** **** **** **** *.
- ******: ******** *** **** **** **** ***; ****** **** any ** *** ******* ** *** ******. *** *****, **'** talking **** ******** ***; ********* *** ****** ********* ** *** edge.

********* *'* ** **** ********** ** ***** ******** ***** **'* a ***** **** ******* ****, *** **** ********** ** ****** models **** ****** ************ / ******. **** ***** ***'** **** get **** ******* ** *** ****'** *** (**** ** ***, OpenVINO ** *****, ***).

*** ******** ** *** ********* ** ******* *** ** ***** that *** **** ** ******* *** ****, **** *** ************, for ********?

****'* * ****** **** ********. *'** **** ** *** *** for ** ****** **** ** * **** **** ******** & reply **** ** * **** ***.

********* *****. ***** ***. * ***** **** ** ******* * similar ********** ** ***** ********** **** ******* ***** *********.

****** ** *** *** ***** ***** *** *** ****** **** security ****?

****, **** *** **** **** ****** (**** ** *** ******), follow *** ***** ************, *** **** **** *** ****** **** the ****/** ********* (******* ** *********** *** *********** *******). *'** keep **** **** ******* & *** ** ******* ** *******, to **** ** **** ** **** ** ****** ****.

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

* ** **** ******* ** *** ******* ** **** **** now ** ***** ** **** ********. *** ** ***** **** experience ** **** *******. **** ***** *** **********.

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.

Most Recent Industry Reports

Repositionable Multi-Imager Camera Shootout - Avigilon, Axis, Dahua, Hanwha, Hikvision, Panasonic, Vivotek on Jun 19, 2019
Repositionable multi-imager cameras are one of the fastest growing segments in video surveillance, with a slew of new offerings being recently...
Genetec Synergis Cloud Link - Complex, Costly and Confusing on Jun 18, 2019
Genetec's Synergis Cloud Link is complex, costly and confusing compared to competitor access control architectures. Inside this note, we examine...
Startup Vaion Launching End-to-End AI Solution Backed with $20 Million Funding on Jun 17, 2019
An EU / USA video surveillance startup, Vaion, founded by ex-Cisco Senior Directors is launching an end-to-end VSaaS platform with $20 million in...
Biometrics Usage Statistics 2019 on Jun 17, 2019
While face and fingerprint recognition are used regularly for smartphones, it is not as common in physical security. In this note, we examine...
The Scheme Hikvision and China Importers Use To Avoid Tariffs on Jun 17, 2019
Hikvision and numerous China importers are avoiding 25% tariffs by including an SD card slot in their IP cameras to claim they are 'digital still...
Sighthound Transforms Into Enterprise AI Provider Profile on Jun 14, 2019
Sighthound is now rapidly expanding its R&D team, building an enterprise AI service. This may come as a surprise given their origins 6 years...
ADT Eliminating Acquired Brands, Unifying Under 'Commercial' Brand on Jun 14, 2019
ADT is eliminating the brands of the many integrators it has acquired over the past few years, including Red Hawk, Aronson Security Group (ASG),...
NSA Director Keynoting Dahua and Hikvision Sponsored Cybersecurity Conference [Canceled] on Jun 13, 2019
The technical director for the NSA’s Cybersecurity Threat Operations Center will be keynoting a physical security cybersecurity conference that is...
Farpointe Data Conekt Mobile Access Reader Tested on Jun 13, 2019
California based Farpointe Data has been a significant OEM supplier of conventional access readers for years to companies including DMP, RS2, DSX,...
Embattled $400 Million China Funded Philippines Surveillance System Proceeds on Jun 13, 2019
An embattled 12,000 camera surveillance system project that will cost ~$400 million will proceed.  The project contract was awarded, had its...

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