client-side face recognition / facial analysis
face-api.js is a client-side JavaScript API for face detection, face recognition, face landmarks, expression recognition, age and gender estimation, running in the browser and Node.js on TensorFlow.js.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose this maintained TensorFlow.js library for browser/Node face analysis when you also need body, hand, iris and pose tracking in the same runtime.
Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it for browser-side face recognition with liveness detection when an ONNX Runtime Web/OpenCV.js stack is preferable to TensorFlow.js.
Face Recognition SDK Javascript using ONNX Runtime Web and OpenCV.js (Face Detection, Face Landmarks, Face Liveness, Face Pose, Face Expression, Eye Closeness, Age, Gender and Face Recognition)
Choose it when you need a maintained server-side Python face recognition and attribute analysis library instead of an in-browser JavaScript API.
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Choose it for native Android/Kotlin face recognition and liveness when a browser/TensorFlow.js solution is not appropriate.
Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks
Choose it when you want a modular Python perception library that includes face recognition as part of a broader CV toolkit.
Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
Choose it when you want a Docker-deployed, language-agnostic face recognition service with REST/UI instead of an in-process JavaScript library.
Leading free and open-source face recognition system
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Older Python alternative for face recognition/attributes when you need a Python-only module and can accept unmaintained code.
face recognition, detection of facial attributes (age, gender, emotion and race) for python.
Choose it for C++ age/gender prediction only when you need a native subset and do not need face recognition.
Predict Age and Gender of people from images | Determination of gender and age
Older Keras research code for age/gender estimation; valid if you need academic Python baselines rather than a maintained API.
Keras implementation of a CNN network for age and gender estimation
Old multi-task research code for smile/age/gender classification; useful only for educational or academic reproduction, not as a real product dependency.
Multi-task learning smile detection, age and gender classification on GENKI4k, IMDB-Wiki dataset.
Older Python research framework for composing face recognition/detection models; choose for prototyping but not for current production.
libfaceid is a research framework for prototyping of face recognition solutions. It seamlessly integrates multiple detection, recognition and liveness models w/ speech synthesis and speech recognition.
Python/PyTorch transformer research model for face parsing/attributes/landmarks; choose only for Python-based facial-analysis research without identity recognition.
[ ICCV 2025 ] FaceXFormer: A Unified Transformer for Facial Analysis
Research model code for age estimation only; choose only for age-focused Python/CV experiments, not full face recognition.
Exploring the Limits of Compact Model for Age Estimation. CVPR2019
Stale .NET face recognition API; choose only for C#/.NET projects where browser JavaScript is not an option.
The world's simplest facial recognition api for .NET on Windows, MacOS and Linux
Older on-device C++ mobile SDK for face detection/landmarks/attributes; choose for native mobile builds that do not require identity recognition.
TengineKit - Free, Fast, Easy, Real-Time Face Detection & Face Landmarks & Face Attributes & Hand Detection & Hand Landmarks & Body Detection & Body Landmarks & Iris Landmarks & Yolov5 SDK On Mobile.
Older Keras/OpenCV face detector plus emotion/gender classifier; choose only for those narrower Python tasks.
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
A stale real-time webcam age/gender demo, not an embeddable library.
Real-time estimation of gender and age
A surveillance/webcam demo application for emotion, age and gender, not a reusable software library.
Computer Vision module for detecting emotion, age and gender of a person in any given image, video or real time webcam. A custom VGG16 model was developed and trained on open source facial datasets downloaded from Kaggle and IMDB. OpenCV,dlib & keras were used to aid facial detection and video processing. The final system can detect the emotion, age and gender of people in any given image, video or real time webcam
A C++ demonstration application for face recognition/liveness, not a library you can drop into your own code.
This repository contains a C++ application that demonstrates face recognition, 3D face liveness detection (anti-spoofing) capabilities using computer vision techniques. The SDK utilizes OpenCV and dlib libraries for efficient face detection and recognition.
An old iOS demo application for age/gender classification, not a reusable face-analysis library.
👀 iOS11 demo application for age and gender classification of facial images.
A real-time webcam emotion analysis demo, not an embeddable library.
Human Emotion Analysis using facial expressions in real-time from webcam feed. Based on the dataset from Kaggle's Facial Emotion Recognition Challenge.
These projects were analysed and named face-api.js among their alternatives. The relationship is not symmetric — how face-api.js rates them is a separate judgement, made when face-api.js is analysed in its own right.
calls face-api.js “when you need a widely known JavaScript face detection/recognition API and can accept an unmaintained legacy library.”
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
calls face-api.js “Older but still used JS face recognition library for in-browser/Node projects; choose it if you accept an unmaintained offline solution.”
Leading free and open-source face recognition system