New Facial Recognition Technology from Herta Enables Subject Identification Even While Wearing a Mask

CCTV Surveillance partners and leaders in facial recognition solutions for crowded environments, Herta, have recently launched a new version of its facial recognition algorithms that can correctly identify people who wear facial masks.

The company had been working on the issue of partial occlusions for some time and, following the worldwide outbreak of coronavirus (COVID-19), development has been accelerated to launch a version of the software that helps provide an accurate identification under these conditions.

Based on Deep Learning technology, Herta’s algorithms provide very high identification rates, especially in identity verification tasks and their reliability is very high, even when people hide a large part of their face. It is worth noting that the most differential part of the human face is in the eye region.

The launch of this software is key for automatic passenger identification systems, such as border control with the passport. This way it will not be necessary for the person to remove the mask, avoiding possible contagion or long waiting times. Its application, in general, extends to any type of access control or identity verification system.

Herta expects that the impact of this new technology in the market will be very important worldwide and that it will be massively used in environments such as transportation, health, government, events, sports stadiums or in the gaming sector.

CCTV Surveillance – The experts in deploying Facial Recognition CCTV systems

The Facial Recognition CCTV solution supplied by CCTV Surveillance dynamically compares images of individuals from incoming video streams against those stored in a predefined access control list and immediately sends alerts when a positive match occurs.

The technology yields a very good level of performance despite partial occlusions of the face, the use of glasses, scarves or caps, changes of facial expression, and moderate rotations of the face. Moreover, it does not allow users to be impersonated using photographs.

This biometric access control technology is the perfect solution to control the access to restricted security areas, especially since we’re talking about a completely automated system that requires very little interaction with the operator.

Our Facial Recognition CCTV system can be easily integrated with existing ID management products and enables administrators to easily create Whitelists/Blacklists for specific areas, while subjects can be very easily enrolled from one or more photographs.

The system fully supports runtime alarm management, is highly tunable (control based on time-frames, sequentially, etc) and even allows alarms to be exported to common formats (PDF, Excel) and remote devices (mobile, PDA, tablet, security control centre).