Amazon Rekognition Facial Detection Tested

By IPVM Team, Published on Dec 03, 2018

Amazon's Rekognition service has announced improvements, that if accurate, would be a significant advance over conventional facial detection.

amazon recognition

In particular, Amazon claims:

Amazon Rekognition can now detect 40 percent more faces – that would have been previously missed – in images that have some of the most challenging conditions described earlier... These aspects might include pose variations caused by head movement and/or camera movements, occlusion due to foreground or background objects (such as faces covered by hats, hair, or hands of another person in the foreground), illumination variations (such as low contrast and shadows), bright lighting that leads to washed out faces, low quality and resolution that leads to noisy and blurry faces, and distortion from cameras and lenses themselves. [emphasis added]

IPVM developed a dataset of 100+ 3-second video clips:

facial detection dataset 2

These clips are done across a number of common real-world scenarios:

  • Day light (200 lux)
  • Low light (1 lux)
  • Side tilt (from 0° to 90°)
  • Down tilt (from 0° to 30°)

We compiled various combinations (such as 200 lux, 15° side tilt, 22° down tilt or 1 lux, 75° side tilt, 30° down tilt, etc.).

We then ran tests of these 100+ clips across facial detection approaches:

  • HAAR
  • HOG
  • Openvino (specifically the face-detection-retail-0004 model on Intel i7 and Myriad X chips expanded upon from our NCS2 test)
  • Amazon Rekognition

Inside, we explain full results and key variances in performance.

Key ********

****** *********** ****** ********* accuracy *** *** ****** than *** ****** ****** including ****** ** **** of ********:

facial detection overall accuracy

*** ****** *** ********* quite '***' *** **** of *** ******** ** used **** ***** ****, including *** ********* *** bad ******.

*** *******, **** ** segment *** ****** ** key ********** ****, **** for ****** ***********, ***** differences ** *********** ******* are *******:

rekognition accuracy segmented

**** ******* *** *** severe ****** ******** ***, with '****' ***** *********** at ****** **% ***** low ***** *********** ** under **%.

***** *********** *** ********* in ****** ********* ********, it ***, *** *** away, *** *******, ** two ****** ** ********* versus ******** *** **** running ** ** **:

facial detection fps

*********** ** **** ****** than *** ***** ******** as *** *********** ***** service ******** *** ***** to ** **** ***** to *** ***** *** other ******** *** ** done ******* / ** the **** / ***** the ****** **. ** examine ***** *********** ******* in *** ***** ******* of **** ******.

********

*****, ** ******* ** 100% ******** *** ****** Rekognition, ***** ** ****** strong *********** *** **** is **° **** *** 45° **** **** **** the ******:

[video-to-gif output image]

****, ** ******* ** 59% ******** (******* ~* out ** ** ****** correctly ******* * ****) for ****** ***********, ****** a ***** ********* ** steep **** *** **** tilt **** *** *******'* head ****:

*** ***** ******, ** noted, **** **** **** challenging **** *** ***********. For *******, **** * out ** ***** * frames *** * **** accurately ******** ****** **** a ***** ***** *** the ****** / ********:

*******, *** ** *** few **** ************ *** Rekognition *** ** **** test ********, ****** *** light, *** ******* ****** straight ******* *** ****** but ***** **** *** not ******** ** ***:

Accuracy ***********

*** ******** ****** **** is ************** *** * simplification. *********** **** ********* evaluation **** * ****** called"**** ******* *********" (***), ***** ******** ***********-**-******* on ****** **** ********* datasets ************** ** ****** **** bounding-box ******* (********* ****** "Intersection **** *****" ** IoU) *** ******* **** box ********* ******** * face. ** ****'* ***** library, **** **** ****** has *** **** (***** frame *** * ****, and ***** ** **** one). ***** ****, ** can *** * ****** heuristic *** ********: ** how **** ****** *** a **** ******** (******** / *****-***** = ********). This ** *** *******: in **********, ** **** not ******* *** ***** positives (* **** ** detected ***********, **** ** the **** ** ** the *******'* *****). **** happens ****** - ** we ***** **** *** heuristic. ** ****** ** more ******* **** ********** (lux, *****, ***) ******* having ** ***** ******** boxes *** ***** ***** of *** *******.

FPS ***********

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

  1. ****** *** ***** ** Amazon **
  2. ***** *** *****
  3. ***** *********** (******** ** to *** ** ****, registering *****->***********)
  4. **** *** *****, ********* FPS

* **** ****** ******** for ************ ***** ** to ****** ****** ******** via*******->***********. **** ***** *** the ********** ******** ** a *****-**-***** *****, ***** our ***** ***** *** networking ******** **** *** FPS *********** ********. ** such, *** *** ***********, already **** ***, ***** be **** *****.

***** ** **** ************, this ** * ***** point ******* ***********, ** others ** *** ** a *******. *** *******, one *** *** ***-***** hardware *** ****** ******* performance. *** ***** ****** in **** ******* *** on ****** * ** Intel ** ******* (****-***) devices, ** **** *********** trade-off ** *********-*********. ************, Rekognition ** * ******* service, ***** *********** * model (**** ********'* ****-******-****) takes **** ************* *** setup. ** ***** ****-**** performance **** *********** ** unlikely (****: ** *** still ************* ** **** is ********), *** ***-****-**** applications, *********** ***** ** quite ******.

*******

*** * ****-**** ***** surveillance ***********,*********** ************ ** ***** **** but *** ***** ************ where **** ********** ***** processing ** ******, ** could ** *** **** affordable **** **-**** **********. For *******, *********** ******* for **-**** (*. ********) is $*.** *** * min ** **** ****** video ********. **** **** just **% ******** ** analyze (*.*., *,*** ******* in * *****), *** monthly **** ***** ** ~$50 (*,*** * **% x $*.**) **** *** the **** *********.

** *** ***** ****,****** *********** ****** ******* features********* ****** ***********, ****** analysis (***, ******, *******), object *** ********** *********, etc. **** **** ********* provider ****** ** *** have ** ***** ** likely ** ******** ** compete **** ***** ***********.

********

**** ** *** *** of ****'* *** ****** of **** ******** *****, starting ********** ********* ******,***** ****** ******* ***** 2 / ******** ** Test*** *** ****. ** are ******** * ******* of *** ***** ** the ******** ******. *** feedback, ******** ** *********, please *** ** *** comments.

Comments (8)

John Honovich

IPVM | 12/03/18 01:52pm

*** ***** ** *** interested ** *** ************,***** *** *** *** class **** ****:

deep learning webinar2

***** **** ** ********** fundamentals ** **** ** our ******** ****** ** provide ************* ******** *** education, ** ******** ** our ******* *****.

Undisclosed Manufacturer #1

12/03/18 02:50pm

*** *** ******* **** running *** ********** **** IR *********** **? **** cameras ***** ****** ** IR *********** (** **** have *** ******) ** 1 ***

John Honovich

IPVM | In reply to Undisclosed Manufacturer #1 | 12/03/18 09:02pm

** *** *** ** any ** ******** *** we **** *** **** in ****** *****.

Avatar

Matthew Del Salto

BLACKBOX USA
12/03/18 03:12pm

**** **** ***** **** integrate ** **** **** if **** *****'* *******.

Undisclosed #2

12/03/18 07:45pm

** ***** *** *** you *** **** *** of **** *** ***** used ** *** ***** for **** ***** ** download *** *** **** their *** ********* *******?

Undisclosed Manufacturer #3

In reply to Undisclosed #2 | 12/03/18 08:02pm

* ***** **** ***** be * ****** ***** way ** ******* ********.

John Honovich

IPVM | In reply to Undisclosed #2 | 12/03/18 09:03pm

** ***** ******* *** dataset *** **** *** decided ***.

Undisclosed #4

04/08/20 05:51am

**** **** **** **% activity ** ******* (*.*., 4,380 ******* ** * month), *** ******* **** would ** ~$** (*,*** x **% * $*.**) just *** *** **** analytics.

****'* *** *********** *** "10%" ****** ***** ** this ***********? *,*** ******* itself ** **% ** total ******* ** * month.

Read this IPVM report for free.

This article is part of IPVM's 6,596 reports, 889 tests and is only available to members. To get a one-time preview of our work, enter your work email to access the full article.

Already a member? Login here | Join now

Related Reports

Face Detection Shootout - Dahua, Hanwha, Hikvision, Uniview, Vivotek on Jul 30, 2020
Face detection analytics are available from a number of manufactures...
Bias In Facial Recognition Varies By Country, NIST Report Shows on Jul 15, 2020
While many argue that face recognition is inherently racist, results from one...
Herta Facial Recognition Plus Masks Tested on Aug 19, 2020
Masks increase face recognition errors, but facial recognition developer...
Clinton Public View Monitor (PVM) Mask Detection Tested on Jul 09, 2020
Face mask detection, or more specifically not wearing one, is expanding...
Face Shields Impact On Temperature Measurement And Mask Detection on Jul 27, 2020
First, the use of face masks, and now, plastic face shields are rising...
Exacq "Facial Matching" Facial Recognition Tested on Sep 03, 2020
Exacq is claiming "Accurate Recall of Every Noteworthy Person of Interest"...
Injes Tiny Temperature Terminal Tested on Jul 17, 2020
While temperature terminals have trended bigger, the Injes DFace801 is...
TVT Temperature Measurement Terminal Tested on Jul 23, 2020
While Dahua and Hikvision get the most attention for China temp products,...
Avigilon Elevated Temperature Detection Camera Tested on Sep 17, 2020
Avigilon has entered the temperature screening market with the release of...
Face Masks Increase Face Recognition Errors Says NIST on Aug 04, 2020
COVID-19 has led to widespread facemask use, which as IPVM testing has shown...
Hanwha AI Object Detection Tested on Sep 28, 2020
Hanwha has added detection and classification of people, cars, clothing...
Hanwha Face Mask Detection Tested on Jul 01, 2020
Face mask detection or, more specifically lack-of-face-mask detection, is an...
Verkada Video Analytics Tested 2020 on Oct 08, 2020
In 2019, Verkada released people and face analytics but our testing then...
The US Fight Over Facial Recognition Explained on Jul 08, 2020
The controversy around facial recognition has grown significantly in 2020,...
FaceFirst Problems And Layoff on Oct 01, 2020
FaceFirst, a US company and one of the oldest ongoing facial recognition...

Recent Reports

Consultants Online Show LIVE Today! on Oct 27, 2020
IPVM's 7th online show will feature 20+ consultants and recruiters presenting...
Eagle Eye Networks Raises $40 Million on Oct 27, 2020
Eagle Eye has raised $40 million aiming to "reinvent video...
Hikvision Q3 2020 Global Revenue Rises, US Revenue Falls on Oct 27, 2020
While Hikvision's global revenue rises driven by domestic recovery, its US...
VICE Investigates Verkada's Harassing "RawVerkadawgz" on Oct 26, 2020
This month, IPVM investigated Verkada's sexism, discrimination, and cultural...
Six Flags' FDA Violating Outdoor Dahua Fever Cameras on Oct 26, 2020
As Six Flags scrambled to reopen parks amid plummeting revenues caused by the...
ISC Brasil Digital Experience 2020 Report on Oct 23, 2020
ISC Brasil 2020 rebranded itself to ISC Digital Experience and, like its...
Top Video Surveillance Service Call Problems 2020 on Oct 23, 2020
3 primary and 4 secondary issues stood out as causing the most problems when...
GDPR Impact On Temperature / Fever Screening Explained on Oct 22, 2020
What impact does GDPR have on temperature screening? Do you risk a GDPR fine...
Security And Safety Things (S&ST) Tested on Oct 22, 2020
S&ST, a Bosch spinout, is spending tens of millions of dollars aiming to...
Nokia Fever Screening Claims To "Advance Fight Against COVID-19" on Oct 22, 2020
First IBM, then briefly Clorox, and now Nokia becomes the latest Fortune 500...
Deceptive Meridian Temperature Tablets Endanger Public Safety on Oct 21, 2020
IPVM's testing of and investigation into Meridian Kiosk's temperature...
Honeywell 30 Series and Vivotek NVRs Tested on Oct 21, 2020
The NDAA ban has driven many users to look for low-cost NVRs not made by...
Ubiquiti Access Control Tested on Oct 21, 2020
Ubiquiti has become one of the most widely used wireless and switch providers...
Avigilon Aggressive Trade-In Program Takes Aim At Competitors on Oct 20, 2020
Avigilon has launched one of the most aggressive trade-in programs the video...
Mexico Video Surveillance Market Overview 2020 on Oct 20, 2020
Despite being neighbors, there are key differences between the U.S. and...