Welcome to FindFace Server’s documentation!

FindFace Server is a set of services for video analytics. FindFace Server is not a turnkey solution. It does not contain business logic and a user interface.

Being integrated into specific solutions, FindFace Server can make for accomplishing diverse goals. Some of these goals are biometric identification and access control, customer analytics, customer offer tailoring, offline retargeting, managing whitelists/blacklists, sorting and optimizing media libraries, borrower scoring, crime prevention, employee productivity control, building SafeCities, to name a few.

FindFace Server will be of interest to independent software vendors (ISVs), system integrators, enterprise IT customers, and original equipment manufacturers (OEMs). It can be harnessed in numerous areas, such as retail, banking, social networking, entertainment, sports, event management, dating services, video surveillance, public safety, homeland security, and many others.

FindFace Server can detect, identify, and analyze different objects in the video. Here are just a few of them:

  • Human faces, along with recognition of such facial attributes as gender, age, emotions, glasses, face mask, beard, and many others.

  • Human bodies (silhouettes), along with recognition of clothing type and color.

  • Vehicles, with recognition of such vehicle attributes as make, model, body style, color, license plate number, and others.

  • Snow pile, streetlight, graffiti, pet faces, shopping cart, visible gas, fire, bear, container, garbage, trash bin, and others.

Furthermore, it is possible to integrate 2D anti-spoofing system, which ensures that it is a live person in front of a camera and eliminates the possibility of fraud using images on paper or mobile device screens.

Core Features

  • AI-based platform.

  • Fast and robust AI-based object detection in still images and video.

  • Fast and accurate AI-based object identification and verification.

  • Scalable and fault-tolerant feature vector and metadata storage supporting sub-linear search time.

  • AI recognition of gender, age, emotions, glasses, beard, face mask, and other face and body attributes.

  • User-friendly APIs hiding complexities of distributed architecture.

  • AI face liveness detector.

  • Customized object processing directives.

Deployment environment

  • Single- and multi-host deployment. Almost infinite scalability.

  • Network or on-premise licensing.

  • CPU- and GPU-based acceleration for your choice.

  • Integration via HTTP API.

This guide is intended for developers and system integration engineers who are going to integrate the FindFace Server functionality into their systems.

To get a general idea of the deployment process, first, take a look at the steps to object recognition. Let’s get started!