Analysis updated 2026-05-18
Log into a Windows 10 or 11 PC using face recognition from a standard webcam instead of a password.
Audit or modify open source facial recognition login code instead of relying on a closed system.
Set up fast, locally processed face login with no data sent to any external server.
| harmanrodee/openfaceunlock---native-face-login-for-windows-10-11 | 9veedz/4leggedspiderbot | akashsingh3031/striver-sde-challenge-2023 | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | C++ | C++ | C++ |
| Last pushed | — | — | 2023-06-19 |
| Maintenance | — | — | Dormant |
| Setup difficulty | hard | hard | easy |
| Complexity | 4/5 | 4/5 | 1/5 |
| Audience | developer | vibe coder | developer |
Figures from each repo's GitHub metadata at analysis time.
Building from source requires Visual Studio plus the OpenCV and ONNX Runtime SDKs, and installs system-level Windows components.
OpenFaceUnlock is an open source program that lets you log into Windows 10 or 11 by showing your face to a regular webcam instead of typing a password. It plugs directly into the Windows lock screen using a special file called a Credential Provider, and all the face recognition happens locally on your own computer, with no data sent anywhere else. Because the source code is public, anyone can inspect exactly how it works. The project is built from three parts that work together. A small C++ component registers itself with Windows so a face unlock option appears on the lock screen. A separate native engine handles the camera, detects your face, measures its key landmarks like the eyes and mouth, and turns your face into a numeric representation using a model called ArcFace, then compares that against a saved reference to decide if it is a match. A third component, a C# desktop application, is what you use to set everything up: it validates your existing Windows password, encrypts and stores it securely using Windows' own built in encryption, and registers the face unlock component with the operating system. To keep the face check fast the moment you reach the lock screen, the installer sets up a background task that preloads the recognition software into memory as soon as your computer starts up, so there is no delay when you actually try to unlock it. When your face is recognized, the program retrieves your encrypted stored password and passes it to Windows to complete the login automatically, the same way it would if you had typed it yourself. Setting this up from source requires Visual Studio, along with the OpenCV and ONNX Runtime software libraries, and the README walks through building each of the three components and placing the resulting files into an installation folder. The project is released under the MIT license.
An open-source Windows lock screen add-on that lets you log in using your webcam and local facial recognition instead of a password.
Mainly C++. The stack also includes C++, C#, ONNX Runtime.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.