AI Face Recognition

Facial recognition system is a technology capable of identifying or verifying a person from a digital image or a video frame from a video source. There are multiple methods in which facial recognition systems work, but in general, they work by comparing selected facial features from given image with faces within a database.

OUTCOME

module fr.dll

it’s an intelligent dynamic and cross-platform face recognition and detect library according to a pre-configured base of people (residents, staff, customers, etc.).

~0.1
sec/frame – effective face detection system that provide high percentage of correct detections, and low false detection rate in short time.
~0,2
sec/face learning features of each face what allow to form a database of people’s faces (DB) and check every detected face in real time.
~97,5%
high recognition accuracy allows to minimize false positives, effectively use the face recognition module to solve the tasks.
500k
faces per second are searched in the faces database – the module works both as part of a single server, and in multi-server system with a single database of persons.

Technologies

C/C++
Machine learning
Dlib
DLL
Solution: Fighting with fraud

Face recognition module allows fight fraud effectively in retail. Using the so-called “black list”, which includes thieves photos and scammers, security department can promptly accept measures when such a person appears directly on the doorstep of the store

Solution: Work with VIP clients

Face recognition module used to alert VIPs appear (e.g.important customer at the bank or regular customers) and may used to improve customer service.

Solution: Access Control System

used for protection with adding biometric identification. When integrating with ACS to card identification access added feature checks using face recognition. When integrated with ACS, the face recognition module can be used to ensuring the passage of employees through turnstiles.