DEVELOP PRODUCTS
WITH FINDFACE SDK
FUNCTIONALITY
The FindFace SDK is a C library that provides access to the cutting-edge face recognition technology based on neural networks. The SDK allows you to quickly and accurately solve the 3 key tasks of face recognition:
Face detection
Finds face fragments in an image and returns a bounding box and control points (eyes, nose, corners of the mouth) for each fragment.
Biometric sample extraction
500 ms is the time needed to extract a face biometric sample and save it in a temporary binary format. The sample can be later saved to a database and used for face verification.
Verification
It takes ~75 ns to compare 2 biometric samples and estimate the probability of their belonging to the same person.
Liveness check
Distinguish a live face in front of a camera from a photo on paper or mobile device screen.
Face attributes extraction
Recognize age, gender, emotions, glasses, beard, and other attributes.
ADVANTAGES
SYSTEM REQUIREMENTS
CPU/GPU
CPU with AVX support/NVidia video card with 6 Gb of video memory for more accurate calculations, 3 Gb of video memory for quicker calculations
RAM
~3.5 GB RAM
OS
Windows 7, 8, 10 (x64), Linux Ubuntu (x64)
TYPICAL CASES
DETECTOR OPERATION EXAMPLES
Detecting a face means locating it in a digital image. Even though a face is small, semi closed, blurred or turned away from the camera, a good detector will find it.
AT A DISTANCE
DETECTION
UNDER COMPLEX CONDITIONS (POOR LIGHTING, BLUR)
KEY FEATURES
Highest accuracy even with the factors that change appearance:
Biometric sample extraction and verification
Biometric sample extraction is a process of obtaining the distinctive features of a particular face from an image using neural networks. The result of this process is a unique array of numbers that describes a face, known as biometric sample, feature vector or face descriptor. It can be further compared to another array of numbers to determine the degree of similarity between the two faces. Look at the real verification cases and acknowledge the algorithm error-free operation in non-ideal conditions with various appearance changes.
FACE FROM SURVEILLANCE CAMERA
KNOWN FACE
FACE FROM SURVEILLANCE CAMERA
KNOWN FACE
FACE FROM SURVEILLANCE CAMERA
KNOWN FACE
CODE
SAMPLE
SUPPORT