Face SDK

Software Development Kit for Face Recognition.

Cross-platform face recognition library for detection, tracking, liveness check and identification. Integrates seamlessly on servers, mobile and edge devices.

Live Demo

Camera Feed

Match — 99.2%

id3 Face SDK

1 face detected — 8 ms

68 landmarks — 3 ms

Template: 148 bytes — 20 ms

Score: 99.2% — Match ✓

Performance

Optimized AI models delivering fast execution on mobile devices and high precision for large-scale identification.

Mobile Execution

Device	Time
iPhone 12	9 ms
Google Pixel 6	68 ms
Fetian FP20	203 ms

Template size: 140 or 268 bytes

Large-Scale Identification

Metric	Value
False Match Rate	0.000001
False Non-Match Rate	0.5%
Matching Speed (1M)	45 ms

On NVIDIA GTX 1080 Ti

Built-in Intelligence

Face Capture

Compatible with a wide range of cameras from leading manufacturers, ensuring versatile and comprehensive biometric data acquisition.

Face Tracking

Provides precise and accurate face detection, capable of real-time processing and continuous monitoring with robust performance even under challenging conditions.

Facial Analysis

Offers multiple face analysis functionalities, including landmarks estimation, pose estimation, mask detection, and ICAO-compliant facial attributes determination.

Liveness Checks

Utilizes accurate passive and active liveness detection methods to protect against biometric fraud, such as presentation attacks using photos or videos.

Feature Extraction

Extracts facial features from detected faces, producing a compact face template for efficient face matching.

Face Recognition

Ensures accurate identification by matching detected faces against a database with ultra-fast performance in both one-to-one and one-to-many search modes.

Core Technology

Our face recognition engine combines optimized AI models with high-precision algorithms, delivering outstanding performance across all platforms. Templates among the smallest on the market enable deployment on resource-constrained devices.

C++

Python

Java

Kotlin

Swift

Dart

Windows Linux macOS Android iOS

NIST FRTE Evaluation

id3 Technologies face recognition algorithm has proven excellent tradeoff between accuracy, speed and template size in the NIST ongoing Face Recognition Technology Evaluation (FRTE).