What Does 3VR Face Recognition Test Results Mean?

Author: John Honovich, Published on May 06, 2009

Recently, results from a facial recognition test for the Korean National Police were reported widely by 3VR of obtaining: "85-92 percent accuracy in recognizing and matching faces in a few crowded, highly-trafficked public train stations in Seoul."

The manufacturer claims these results are the best ever in any public video facial recognition study (compared to only 60% historically). One of the security magazine editors suggested that this was reason to "change the standard analytics copy

A Korean National Police spokesman praised the results, expressing interest and confidence in deploying facial recognition widely. It is always impressive to see end users expressing confidence in new surveillance technologies.

The Importance of Test Results

In the security industry, test results are key benchmarks for buyers and integrators in evaluating technologies. Improvements in test results can be important drivers for expanding the use of technologies. As such, accuracy and clarity in test results are essential in ensuring successful deployments.

In facial recognition test results, it is common that detailed reports are released and in-depth quantifications are offered. These tests are often administered by government agencies. (Read a facial recognition overview and examine the 2006 US government study for good examples and background.)

The Korean National Police Test

Three material differences should be considered when comparing the Korean National Police Test to other previous publicly released studies:

  • While the test was sponsored by the Korean government, the tester, SK Networks, is a corporation that sells technology products, not an independent testing agency.
  • The tester, SK Networks, is marketing 3VR products (see SK Networks' marketing website and a 20 page marketing proposal for 3VR products, both dated 2008 [Note: the website has since been taken down]). 3VR reports that they were not aware of these documents and that they have asked SK Networks to remove them from the Internet.
  • No details were publicly provided on false error rates, system setup, or testing methodology. Small variances in any of these elements can result in significantly different accuracy statistics. 3VR reports that a 170 page test result document is available in Korean (NIA pub number NIA 111-RER-07113/2007.12) which they are in the process of translating but have not been given permission to share publicly.

Concerns about The Test

3VR's claim that this test result is the best ever raises concerns. First, since we cannot read the test results, it cannot be assessed how comparable the implementation and design of this test is to leading global scientific studies. Secondly, unlike other facial recognition tests conducted by independent testing agencies, SK Networks sells technology products and has a general interest in promoting the purchase and use of such products.

Setting appropriate expectations for advanced technology projects is crucial, especially when statistics are being cited. This is why the community depends on scientific, independent studies that can be peer reviewed by outside experts.

It is promising to hear end users interested in using facial recognition and pleased with their test results. However, comparable statistical claims require far higher scrutiny and clarity than provided yet for the Korean NPA test results.

Related Reports

Avigilon New COO James Henderson Profile on May 23, 2017
It has been nearly 2 years since the infamous Bryan Schmode 'resigned' as Avigilon COO. Now, Avigilon once again has a COO, promoting James...
Hikvision Marketer Caught Spamming, Fails at Coverup, Fired on May 23, 2017
A Hikvision marketing employee was caught by IPCamTalk trying to surreptitiously disparage IPVM and IPCamTalk. This is an outgrowth of Hikvision's...
ShotSpotter To IPO, Facing Low Revenue and Losses on May 17, 2017
A rare event for North American security manufacturers is upcoming. ShotSpotter is planning to IPO on the NASDAQ, aiming to raise $34.5...
Shark Tank Startup Guard Llama Mobile Panic Tested on May 16, 2017
A Shark Tank TV show appearance has attracted big attention for Guard Llama, a security startup touting a 'panic button' paired with mobile app...
Mobile Video Installation Statistics on May 02, 2017
Mobile video systems - those mounted on buses, trains, cars, boats, etc. - are a niche within video surveillance with its own particular...
Duress Codes For Alarms Systems on May 02, 2017
An alarm system can call for help in the event of an attempted break in, but only if it is armed. If an adversary forces an authorized user to...
Burglar Alarm Zoning Guide on Apr 28, 2017
The function of an alarm panel is to gather information from sensors and respond to this information by triggering actions. While it is possible to...
A Marketing Home Run For Knightscope - Man Attacks Robot on Apr 27, 2017
We criticize Knightscope regularly - their lack of revenue, their trying to fool mom 'n pop investors, their associating themselves with a clueless...
Beware The "Hit List" Ranking on Apr 21, 2017
The hit list. Kirschenbaum's recent newsletter complained about a 'hit list', bemoaning how a company took aim at ADT. Alas, that's the Google...
Failing at Marketing, "ALL HIKVISION PRODUCTS" On Sale on Apr 18, 2017
The ballerinas are out. The price cuts are back. Hikvision is struggling to build a premium brand (i.e., 'The Art of Video Surveillance') so...

Most Recent Industry Reports

Milestone Entry Level Mobile Password Vulnerability Disclosed on May 24, 2017
While many manufacturers have only addressed cybersecurity vulnerabilities after public disclosures were made (or threatened), Milestone has...
How Integrators Use IPVM on May 24, 2017
150 integrators explained how they use IPVM and how it helps them stay informed and improve their business.  The 4 main uses integrators cited for...
Alarm Supervision Guide on May 24, 2017
Burglar alarms can constantly monitor the health of attached circuits, sensors, and devices to ensure that they remain operational. This is known...
Arlo Go Cellular Cloud Camera Tested on May 23, 2017
Totally wireless surveillance cameras are growing but almost all typically depend on a hub and local Internet access. However, many outdoor...
Avigilon New COO James Henderson Profile on May 23, 2017
It has been nearly 2 years since the infamous Bryan Schmode 'resigned' as Avigilon COO. Now, Avigilon once again has a COO, promoting James...
Hikvision Marketer Caught Spamming, Fails at Coverup, Fired on May 23, 2017
A Hikvision marketing employee was caught by IPCamTalk trying to surreptitiously disparage IPVM and IPCamTalk. This is an outgrowth of Hikvision's...
Aura's 'Invisible Ripple' Next Gen Intrusion Detection Tested on May 23, 2017
Aura Home is a startup intrusion detection system, but it claims new, high-tech sensing that monitors the 'invisible ripples' movement creates,...
Pelco Shutting Down Clovis Line, Laying Off 200 on May 22, 2017
Pelco's Clovis facility once turned out some of the industry's most popular products. Now, the facility is mostly building "obsolete" equipment,...
IP Camera - 15 Year Shootout on May 22, 2017
How far have IP cameras come? We bought and tested 4 cameras across the past 15 years to understand how much and where performance has...
Remote Video Monitoring Providers Directory on May 21, 2017
Remote video monitoring can help integrators generate RMR plus end users lower their security costs and/or improve response to critical...

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