Skip to main content

Identity Verification with Facial Recognition

Project description

OpenFaceID - Identity Verification with Facial Recognition

OpenFaceID is an open-source identity verification project that utilizes facial recognition technology to provide a robust and secure solution for detecting and authenticating known faces. This project aims to deliver a seamless and reliable user experience for identity verification in various applications.

Installation

Use the following command to install OpenFaceID:

pip install openfaceid

Getting Started

To get started with OpenFaceID, you can follow the FAISS example below:

import faiss
from openfaceid import face_detector
from openfaceid.vector_stores.faiss import FAISS

# Threshold distance used to determine if a face is considered a match or not.
# In this example, it's set to 0.25, which is specific to FAISS and the test images used during testing.
# You may need to adjust this threshold based on your dataset and vector store.
# A lower value means stricter matching, while a higher value allows for more leniency in matching.
_DISTANCE_THRESHOLD = 0.25

fd = face_detector.FaceDetector()

# Get all image ids and vector embeddings of existing faces, i.e. loading from a database
all_embeddings = []

# Initialize the FAISS index and add all image embeddings to it
dimension = len(all_embeddings[0][1])
index = faiss.IndexFlatL2(dimension)
faiss_store = FAISS(index)
faiss_store.add_embeddings(all_embeddings)

# Load the image and perform identity verification
# Replace "path-to/new_selfie.jpg" with the actual path to your new selfie image
face_embedding = fd.get_embeddings(image_path="path-to/new_selfie.jpg")
scores, image_ids = faiss_store.search_with_score(face_embedding)
found = scores[0] < _DISTANCE_THRESHOLD

if found:
    print(f"The face has been successfully matched to an existing face with the id of {image_ids[0]}.")
else:
    print("Unknown selfie.")

This code can run when initialising the server. For more examples check ./examples folder.

Contributing

We welcome contributions to OpenFaceID! If you have ideas, bug reports, or feature requests, please feel free to open an issue or submit a pull request. For more information, see CONTRIBUTING.md.

License

OpenFaceID is released under the Apache License 2.0. Please review the license for more details.

Acknowledgements

We would like to express our gratitude to the open-source community and the developers of the underlying facial recognition technology that makes OpenFaceID possible.

Contact

For questions or inquiries, please contact at ahalimkara@gmail.com

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

openfaceid-0.1.4.tar.gz (27.5 MB view details)

Uploaded Source

Built Distribution

openfaceid-0.1.4-py3-none-any.whl (27.6 MB view details)

Uploaded Python 3

File details

Details for the file openfaceid-0.1.4.tar.gz.

File metadata

  • Download URL: openfaceid-0.1.4.tar.gz
  • Upload date:
  • Size: 27.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.11.3 Darwin/22.5.0

File hashes

Hashes for openfaceid-0.1.4.tar.gz
Algorithm Hash digest
SHA256 8ea2bfe983a8da9853c103f5b58b9bf433413ac5d0d8d73baa3a6604882d4f28
MD5 31a56e3927a8961c7769be811e733b14
BLAKE2b-256 2b9cf5a3d5121506c1e0e063ae04445a5079945fa7447901f9bcdceee7af23fe

See more details on using hashes here.

File details

Details for the file openfaceid-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: openfaceid-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 27.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.11.3 Darwin/22.5.0

File hashes

Hashes for openfaceid-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 83e0818ada102a0711b7f9dc0f359d7d3e2d26ad6b8a64e8fb542614a7e6c1f4
MD5 ad73f299e02ee3a3de570d87e45b670d
BLAKE2b-256 e7d45422ade81d453621505354d9db94364f3a5471afe2443be253694aed5755

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page