The world’s leading company in facial recognition solutions for crowded environments, Herta, is launching a new version of its facial recognition algorithms this week 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. Their reliability is very high, even when people hide a large part of their faces. 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 generally 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.
Herta is a world leader in the development of high-tech facial recognition solutions. With headquarters in Barcelona and offices in Madrid, Los Angeles, Montevideo, Mexico City, Singapore and Dubai, the company offers fast, accurate, robust and end-customer-oriented solutions for video surveillance, access control, and marketing requirements. International projects include safe cities, airports, train and subway stations, prisons, banks, casinos, sports stadiums, shopping centers, military, police and forensic applications. Herta has partners in 50 countries and more than 150 certified integrators worldwide.
Herta specializes in analyzing crowded environments, which allows us to detect and identify multiple subjects simultaneously through IP cameras. Our software is fully scalable and compatible with any IP camera, becoming an easy-to-use and accessible tool for any business organization.