Cross-platform face identification library for in-app multi-user authentication.
Identifies users by face in under 300ms. Runs entirely on-device — no cloud.
| Users | Identify All | Quick ID |
|---|---|---|
ios/ Swift Package — FacesKit (Vision, CoreML, AVFoundation)
android/ Gradle library — faceskit AAR (CameraX, ML Kit, TFLite)
react/ React Native module — react-native-faces (TurboModules)
web/ Browser package — @unlikeotherai/faces (Worker + WASM boundary)
examples/ Three standalone RN apps (registration, recognition, debug)
model/ Training pipeline — train your own CoreML + TFLite model
docs/ Architecture, testing, training guide
The model is not included. Everyone trains their own from a dataset of their choice. See Training below.
Register user (6 guided photos)
→ detect face → extract 128-dim embedding → store on device
Extract embeddings only (no store write)
→ detect face per photo → extract embedding → return [[Float]] for external DB storage
Live camera frame (every 3rd frame)
→ detect face → extract embedding → cosine similarity vs. stored embeddings
→ if score > 0.70 → emit login event
Identification, not authentication. Speed over security.
The guided registration UX for the example app is defined in
docs/registration-guided-capture.md.
Add to your Package.swift:
.package(url: "https://github.com/UnlikeOtherAI/Faces.git", from: "0.1.0"),
import FacesKit FacesKit.shared.onMatch = { match in login(userId: match.worker.id) } FacesKit.shared.start()
// build.gradle.kts implementation("ai.unlikeother:faceskit:0.1.0")
FacesKit.onMatch = { match -> login(match.worker.id) } FacesKit.start(context)
pnpm add react-native-faces
import FaceID from 'react-native-faces' FaceID.startRecognition() FaceID.onFaceRecognized((match) => login(match.workerId))
pnpm add @unlikeotherai/faces
import { createFacesRecognitionWorker, createFacesWebRecognition, createRecognitionWorkerClient, } from '@unlikeotherai/faces' const workerClient = createRecognitionWorkerClient(createFacesRecognitionWorker()) await workerClient.initialize({ moduleUrl: new URL('./modelEmbedder.js', import.meta.url).href, expectedEmbeddingDimensions: 128, }) const recognition = createFacesWebRecognition({ workerClient }) recognition.onFaceRecognized((match) => selectWorker(match.workerId))
See docs/web-wasm-recognition.md for the browser Worker/WASM architecture.
The model must be trained before the library works. You provide a face dataset; the pipeline produces a CoreML model for iOS and a TFLite model for Android.
cd model python3 -m venv .venv && source .venv/bin/activate pip install -r requirements.txt
| Dataset | Identities | Images | Notes |
|---|---|---|---|
| DigiFace-1M | 10,006 | 1.2M | Recommended — fully synthetic, zero privacy issues, pre-aligned, scriptable download |
| Glint360K | 360,000 | 17M | Best accuracy, industry standard, scraped from web |
| MS1MV3 | 93,000 | 5.9M | Cleaned MS-Celeb, widely used, scraped from web |
| VGGFace2 | 9,131 | 3.3M | Good pose/age diversity, requires registration |
| CASIA-WebFace | 10,575 | 494k | Smallest, good for quick experiments, scraped from web |
All "scraped from web" datasets carry privacy and consent concerns — images were collected without subject knowledge. Be aware of this for commercial products.
Fully synthetic — Microsoft Research. No real people. Zero privacy concerns.
LFW accuracy after training: ~99.0–99.2%
# Download (~14 GB, resumable) python model/dataset/download_synthetic.py --dst data/raw # Validate and prepare python model/dataset/prepare_synthetic.py --src data/raw --dst data/aligned # Train python model/train.py --data data/aligned --epochs 40 --batch 128 --output checkpoints/
Best accuracy. Available via the InsightFace project.
- Download from InsightFace dataset page
- Extract to
data/raw/(one folder per identity) - Align with MTCNN:
pip install facenet-pytorch python model/dataset/prepare_real.py --src data/raw --dst data/aligned python model/train.py --data data/aligned --epochs 30 --batch 256 --output checkpoints/
LFW accuracy: ~99.6–99.8%
Note: Scraped from the web. Use with appropriate legal review for commercial products.
Cleaned version of MS-Celeb-1M. Widely used in research.
- Download from InsightFace releases
- Convert from MXNet RecordIO format:
# Requires: pip install mxnet
python model/dataset/convert_mxnet.py --rec data/ms1mv3/train.rec --dst data/raw/
python model/dataset/prepare_real.py --src data/raw --dst data/aligned
python model/train.py --data data/aligned --epochs 35 --batch 256 --output checkpoints/LFW accuracy: ~99.4–99.7%
Note: Microsoft took the original MS-Celeb dataset down in 2019 due to privacy concerns. MS1MV3 is a cleaned re-release. Same caveats apply.
Excellent pose and age diversity. Requires registration.
- Register and download from VGGFace2 website
- Extract to
data/raw/ - Align:
python model/dataset/prepare_real.py --src data/raw --dst data/aligned --min-images 10 python model/train.py --data data/aligned --epochs 40 --batch 128 --output checkpoints/
LFW accuracy: ~99.0–99.3%
Smallest dataset. Good for quick experiments and testing the pipeline.
- Download from academic sources (search "CASIA-WebFace download")
- Align:
python model/dataset/prepare_real.py --src data/raw --dst data/aligned python model/train.py --data data/aligned --epochs 40 --batch 128 --output checkpoints/
LFW accuracy: ~98.5–99.0%
# Download LFW for validation # http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz → data/lfw_aligned/ # http://vis-www.cs.umass.edu/lfw/pairs.txt → data/lfw_pairs.txt python model/validate.py \ --checkpoint checkpoints/epoch_040.pt \ --lfw data/lfw_aligned
# ONNX python model/export/to_onnx.py \ --checkpoint checkpoints/epoch_040.pt \ --output model.onnx # CoreML — drops into ios/ automatically python model/export/to_coreml.py \ --onnx model.onnx \ --output ios/Sources/FacesKit/Resources/MobileFaceNet.mlpackage # TFLite — drops into android/ automatically python model/export/to_tflite.py \ --onnx model.onnx \ --output android/src/main/assets/mobilefacenet.tflite
After export, rebuild the iOS and Android projects — the model is bundled as a resource.
| Metric | Target |
|---|---|
| Face detect | < 80ms |
| Embedding | < 120ms |
| Matching (100 users) | < 20ms |
| Total pipeline | < 300ms |
| CPU usage | < 40% |
Three example apps in examples/ demonstrate the full workflow. See docs/testing.md for E2E test instructions using AppReveal.
MIT — see LICENSE.
Training datasets have their own licenses. Check each dataset's terms before commercial use.