Augmenting
Intelligence
NtechLab research team is a group of experts in the field of deep learning and artificial intelligence. We like to invent algorithms which work in unconstrained real-life scenarios
Visit FindFace.PROLearn more about the products based on our algorithm
Our facial recognition algorithms are acknowledged to have the best performance on worldwide independent benchmarks
NIST TOP PERFORMER
IARPA 1st PLACE
scroll
Our algorithms
Face verification100%
Face recognition for verification

The best verification algorithm in the world. Proven by the latest independent testing of face recognition engines.

  1. Winner of the Intelligence Advanced Research Projects Activity (IARPA) Face Recognition Prize Challenge (FRPC). See the report below and a detailed report on nist.gov.

    IARPA FRPC Wild (FMR=0.001 ?)
    ALGORITHM FNMR ?
    1 NtechLab 0.22
    2 XXX algorithm 0.35 (-59%)
    ...10 YYY algorithm 0.68 (-209%)
  2. At the recent Face Recognition Vendor Test, conducted by the National Institute of Standards and Technology (NIST), NtechLab’s face recognition technology showed the best performance on sophisticated datasets – “wild” and “child” – among all participants for large-scale verification.

    NIST FRVT Wild (FMR=0.0001) Child (FMR=0.01)
    ALGORITHM FNMR FNMR
    1 NtechLab 0.271 0.433
    2 XXX algorithm 0.344 (-27%) 0.549 (-27%)
    ...10 YYY algorithm 0.508 (-87%) 0.631 (-46%)
Face identification
Face recognition for identification

The IARPA Face Recognition Prize Challenge found NtechLab to have the world’s fastest algorithm. It is currently the world’s only algorithm with sub-linear search time.





NtechLab’s algorithm works on planetary scale datasets with billions of faces, showing the best accuracy and speed performance:

Search time on huge datasets:

  • 250 million faces in dataset – search time is less than 0.2 sec.
  • 500 million faces – less than 0.3 sec.
  • 1 billion faces – less than 0.5 sec.
Face Detection3 faces found
Face detection algoritms

Our face detection algorithm is renowned for revolutionary speed and accuracy. In a single shot our algorithm processes an unlimited number of faces, perfectly tailored for mass events. It is resistant to lighting conditions, posture, head poses and tilts.

Аge, Gender28 years, male
Age and gender recognition algorithm

Detects a person’s age with 95% accuracy in 5 years’ intervals.

Detects a person’s gender with 99% accuracy.

Age and gender detection can be adopted across a wide range of use cases and markets including targeted offline advertisement, access control and data enrichment.

EmotionsАstonishment
Emotion recognition algorithm

Detects 7 primary and 50 compound emotions of a person. Captures and interprets emotional data to deliver actionable insights.

Emotion detection can be adopted across a wide range of use cases and markets including entertainment and media, client satisfaction measurement.

Algorithm’s quality is proven by 1st place at EmotioNet Challenge 2017.

Our products
FindFace Enterprise Server SDK

Powered by Ntechlab face recognition algorithm, FindFace Enterprise Server SDK effectively processes face recognition and works on the client’s side – no biometric data is transferred or stored by NtechLab. It detects and identifies people’s faces in live video streams and video footage addressing a wide range of business tasks, such as precise people count, demographic information, people flow and client behavior. FindFace Enterprise Server SDK allows for integration into any web, mobile, or desktop application using cross-platform REST API.

FindFace Enterprise Server SDK 2.0 can be adopted across a wide range of use cases and industries including customer analytics, client verification, fraud prevention, hospitality, and access control. It can be deployed across retail, banking, entertainment, sports, event management, dating services, security, public safety, homeland security, and more.

Learn more
FindFace Public Safety

System of intellectual video analytics FindFace Public Safety is specifically designed to ensure public safety on the scale of a metropolis, a region and even the whole country.

FindFace Public Safety is able to simultaneously analyze data from hundreds of thousands of surveillance cameras, instantly distinguishing and storing the meaningful information (people's faces) from video stream.

Such processing allows you to increase the depth of historical data storage by 20–30 times as compared to video storage: data accumulated over 2.5 year period are placed at capacities sufficient to store a monthly video archive.

All face images taken from the cameras are instantly compared to the monitoring database. From the moment of a person’s passing in front of the camera until the notification is being transmitted to a mobile device of a watch officer it takes no more than 2-3 seconds, this allows you to quickly respond to the situation and prevent offenses.

The face search function within the archive accumulated over the entire surveillance period makes it possible to accurately determine the permanent residence of wanted people, identify their usual displacement routes and alleged crime associables.

Advanced analytics features allow you to count unique visitors in the observation area, analyze the socio-demographic portrait of the audience with gender and age identification.

Learn more
FindFace Security

Powered by Ntechlab face recognition algorithm, FindFace Security accurately recognizes faces and runs on the client’s side – no biometric data is transferred or stored by NtechLab. It detects and identifies people in images and live video streams, creating an extra level of security for law enforcement and business organizations. Our solution can be used for access control, fraud and theft prevention, accelerating the investigation of the embezzlement of data and physical assets in a timely manner.

The solution also helps increase customer loyalty and satisfaction through personalized recommendations and anonymous analysis of shoppers’ behavior. FindFace Security can be used in a wide range of areas such as retail, banking and finance, sporting and other mass events, corporate and public safety.

Learn more
Coming soon
Tracks the silhouette and path of a person passing by the camera:
Accurate people count
Effective in big crowds
where people obscure each other
Effective coupled with face recognition
or as a stand-alone
Recognizes a person’s ethnicity

Facial recognition algorithms analyze photographic images for the characteristics visible to an untrained eye. We can determine with good accuracy age, gender and certain emotions, as well as if the person is wearing sunglasses or a mustache. Those classifiers may have practical applications in retail, healthcare, entertainment and other industries by delivering accurate and timely demographic data to enhance the quality of service. Thus the algorithm has the ability to confirm the accuracy of manually entered demographic records, or to narrow the database search.

Contacts
Moscow Office
Russia, Moscow, 123557,
Bol'shaya Gruzinskaya street,
61 building 2

Cyprus Office
Archiepiskopou Kyprianou
and Zakynthou, 2,
Office 1, 6016, Larnaca, Cyprus
Phone
+7 (499) 110-22-54

Work time
from 10:00 to 19:00 Moscow time (GMT+3)