Adam Bannister

Editor, IFSEC Global

Author Bio ▼

Adam Bannister is editor of IFSEC Global. A former managing editor at Dynamis Online Media Group, he has been at the helm of the UK's leading fire and security publication since 2014.
July 23, 2018

Sign up to free email newsletters

Download

Understand the true cost of your video solution

Panasonic’s new deep learning facial recognition platform Face Server is industry’s most accurate yet, NIST tests show

Panasonic Business unveiled its new deep learning facial recognition technology to the European market at IFSEC 2018.

Jointly developed with the National University of Singapore, Face Server’s deep learning core engine is the industry’s most accurate yet, tests by the National Institute of Standards and Technology (NIST) have found.

Face Server can identify faces at an angle of up to 45 degrees to the left or right or 30 degrees up or down, as well as those partially hidden by sunglasses and face masks.

The platform has already been rolled out at Tokyo’s Haneda airport, replacing a fingerprint recognition system at the passport entry gates after three years of verification testing.

Panasonic also unveiled a ground-breaking quad 4K multi-sensor camera and its Video Insight 7 video management system at IFSEC 2018.

Features

  • Identifies faces at an angle of up to 45 degrees to the left or right or 30 degrees up or down, and those partially hidden by sunglasses and face masks.
  • Real-time processing capacity of up to 20 cameras per server and can execute high-speed searches of up to 30,000 registered reference faces.
  • Combined with Panasonic’s iPro Extreme camera range, Face Server uses ‘iA (intelligent Auto) mode’ and ‘best shot feature’ to automatically adjust settings to capture optimal images
  • iA function means image analysis is performed on the camera and only the best images are sent to the server – reducing server and network load and total system cost

Panasonic Business says

“Face Server changes the game in terms of detection accuracy,” said Gerard Figols, Category Manager at Panasonic Security. “Not only does it maintain 90%+ accuracy for faces that are partially covered by sunglasses or face masks, it also recognises faces from photographs that are up to 10 years old.”

The Seagate Surveillance Storage Survey Report 2018

IFSEC Global Exclusive: The State of Surveillance Storage

From the growing quantity of data to new innovations like Artificial Intelligence and machine learning, the surveillance and security landscape is changing.  Download the eBook to identify the accompanying challenges - and to discover just what storage solutions need to offer to meet the evolving needs of security industry professionals, installers and integrators.

Related Topics

2
Leave a Reply

avatar
2 Comment threads
0 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
2 Comment authors
FR ReaderInterested Recent comment authors
  Subscribe  
newest oldest most voted
Notify of
Interested
Guest
Interested

There are now many tests conducted by NIST on face recognition algorithms. There is no reference in this article as to which NIST test Panasonic have achieved the most accurate test result. What was the use case? What was the resolution of the test images? Was it Identification or Investigation mode? Some more details by the author would be beneficial.

FR Reader
Guest
FR Reader

A current check of NIST’s 3 Face Rec test reports (FRVT, FIVE, FR Prize Challenge at http://www.nist.gov/programs-projects/face-projects) show no mention of Panasonic. Can anybody substantiate the claim “Panasonic’s new deep learning facial recognition platform Face Server is industry’s most accurate yet, NIST tests show”?

Sign up to free email newsletters