FindFace Enterprise Server SDK 2.0

The world's best facial recognition technology on your business’s side.
Features|System requirements|R&D

Request SDK trial

The FindFace Enterprise Server SDK 2.0 can be widely applied in a variety cases, 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.

FindFace’s premier face recognition technology offers a wide range of capabilities, including face detection, verification, identification, and detection of age, gender, and emotions. With the highest-rated accuracy in industry, we can ensure that your face recognition needs will be met in the best possible way.

Understanding that speed is just as important as accuracy, we have created technology that can search through a database of a billion faces in less than half a second. It works with photos and video streams alike, using its own brand new video detector.

For demonstration purposes, we offer a self - explainatory GUI and an open - source Android app.It will help you to understand the solution and evangelize it internally if needed.

With all the images and data stored on your servers, you can integrate our solution with minimal time and effort. We offer documentation, a set of tools, and various examples in several programming languages that help you embed face enrollment, identification, and verification capabilities into your system.

Features
State-of-the-art
neural network
FindFace Enterprise Server SDK 2.0 uses a proprietary neural network trained to near-perfection on 20,000,000 photos. Its performs with the highest speed and accuracy, proven by our NIST 2017 certification and MegaFace challenge in 2015. FindFace redefines the industry standards and enables new, previously impossible applications.
Highest
Accuracy
Our unique neural network operates with an error rate as low as 1 in 1,000,000. With a dataset of 10,000, its identification accuracy rate is over 95% and its verification accuracy rate is over 99 %.
(It’s not less than 95% in the vast majority of business use cases.)
Age, gender
and emotions recognition
The FindFace Enterprise SDK 2.0 enables gender, age, and emotions recognition. It detects the gender of a person in a photo with 99% accuracy, and detects age with 95% accuracy within a three-year threshold. Additionally, it enables a person’s primary and secondary emotions detection.
Demo
tools
Our GUI and open-source Android demo app will help you more deeply understand the power of our solution and share it internally if needed.
Fastest Large-
Scale Search
Thanks to the industry's smallest face descriptor (coming in at just 1.28 KB) and our unique proprietary search index, FindFace technology is able to search billions of photos in less than half a second.
On your
hardware
The FindFace Enterpirse Server SDK 2.0 runs with all data stored on your own servers to give your business absolute peace of mind. With cross-platform REST API on board, the FindFace Enterprise Server SDK 2.0 can be easily integrated in any web, mobile, or desktop application in a prompt and unified manner.
System
Requirements
Server System Requirements

(applicable for standalone installation)
CPU: x86-64 with AVX support
RAM: 2 GB plus an additional 1 GB per 1 million faces
OS: Ubuntu 16.04 or later (x64 only)
Virtual machine support: VMware vSphere 5.0 or later

Video detector system requirements

CPU: 1 x 720p (1280×720) stream at 25FPS > i7-6700 (4 phys core CPU)
RAM: > 4 GB
OS: Ubuntu 16.04 or later (x64 only)

Research & Development

Need help developing a product to make your facial recognition idea into reality? Try our Reseach & Development services, or fill out the form below with brief description of your business or project.