Digifort Facial Recognition offers fast and accurate identification.
The Digifort Facial Recognition system, powered by Sentinel, has benefited from developments in artiﬁcial intelligence, biometric technology, Machine Learning and IT price erosion. These factors have contributed to increased recognition accuracy with a reduction in system costs. Facial Recognition is now viable in an ever wider range of applications on a larger scale and in increasingly more challenging environments.
How the Facial Recognition system works.
The Facial Recognition system uses an image or video of a person’s face, ideally taken from the front, to form a recognised person database. An algorithm converts the image or video image into a numeric template. This cannot be converted back to an image for security reasons. Every numeric template is different, even if it is an image of the same person. However, those from the same person are more similar than templates from different people. Images of the same person can be linked on the database to build up an increasingly robust template profile of that person.
When the Facial Recognition system is operating in real-time, templates of people’s faces are taken and compared to those in the database. The technology identiﬁes individuals by matching the numeric template of their face, with all the templates saved in a database, in a matter of seconds.
Digifort Facial Recognition features include:
- Facial recognition in real time using template algorithms.
- Algorithms which allow accurate facial recognition even with face position / posture variations; changes in lighting conditions; alterations of facial features due to beards and hair colour, style and shape; and when people are wearing accessories such as hats or glasses.
- Scalability of the system, which works with many brands of camera.
- Web interface monitoring with alerts in real time and gives the option of accessing information from any integrated system.
- Real-time notiﬁcations in the form of emails, SMS and mobile notiﬁcations.
- Registration of individuals through a mobile phone application using existing images, video footage or recorded events.
- Option for having white list (authorized users) and black-list (unauthorised users) databases for site management and access.
|Digifort Facial Recognition.||
Digifort Facial Recognition technical specification.