https://github.com/verifid/facereg

Python module for face recognition with OpenCV and Deep Learning.
https://github.com/verifid/facereg

cnn-for-visual-recognition computer-vision deep-learning face-recognition hog-features opencv

Last synced: 7 days ago
JSON representation

Python module for face recognition with OpenCV and Deep Learning.

• Host: GitHub
• URL: https://github.com/verifid/facereg
• Owner: verifid
• License: mit
• Created: 2019-01-06T20:52:16.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-02-17T20:41:40.000Z (over 3 years ago)
• Last Synced: 2024-10-07T17:36:48.876Z (about 1 month ago)
• Topics: cnn-for-visual-recognition, computer-vision, deep-learning, face-recognition, hog-features, opencv
• Language: Python
• Homepage: https://facereg.verifid.app/
• Size: 1.57 MB
• Stars: 21
• Watchers: 5
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • License: COPYING

Awesome Lists containing this project

README

        
facereg

=======

.. image:: https://img.shields.io/pypi/v/facereg.svg

    :target: https://pypi.org/pypi/facereg/

.. image:: https://img.shields.io/pypi/pyversions/facereg.svg

    :target: https://pypi.org/project/facereg

.. image:: https://github.com/verifid/facereg/workflows/facereg%20ci/badge.svg

    :target: https://github.com/verifid/facereg/actions

.. image:: https://codecov.io/gh/verifid/facereg/branch/master/graph/badge.svg

    :target: https://codecov.io/gh/verifid/facereg

.. image:: https://pepy.tech/badge/facereg

    :target: https://pepy.tech/project/facereg

**facereg** is a module for face recognition with OpenCV and Deep Learning.

For now it can be used for just images. It is easy to use with a handy feature 

which downloads images from Google for you with given keywords to create dataset/s.

Uses two different technics **CNN** and **HoG** for recognition based on `dlib `_'s

face recognition system with using `face_recognition `_.

**facereg** has totally three different layers and only recognizer has connection on encoder.

|image_layers|

Prerequisites

=============

* `CMake `_

* All dependencies are listed on ``requirements.txt`` and will be installed when you install with **pip**.

Installation

============

* Install module using ``pip``::

    $ pip install facereg

* Download the latest ``facereg`` library from: https://github.com/verifid/facereg and install module using ``pip``::

    $ pip install -e .

* Extract the source distribution and run::

    $ python setup.py build

    $ python setup.py install

Usage

=====

* ``google_images``:

.. code:: python

    import os

    from facereg import google_images

    output_directory = os.getcwd() + '/datasets' # directory path where you want to save photos

    image_paths = google_images.download('michael jordan', limit=3)

* ``face_encoder``:

.. code:: python

    import os

    from facereg import face_encoder

    datasets_path = os.getcwd() + '/datasets'

    encodings_path = os.path.dirname(os.path.realpath(__file__)) + '/encodings.pickle'

    # these are default values for this method

    face_encoder.encode_faces(datasets=datasets_path, encodings=encodings_path, detection_method='cnn')

* ``recognize_faces``:

.. code:: python

    from facereg import recognize_faces

    image_path = 'DIRECTORY PATH OF YOUR_IMAGE'

    names = recognize_faces.recognize(image_path)

    # returns found names from your datasets

CLI Usage

=========

* Download images

.. code::

    # -d: keyword, -l: limit

    $ python -m facereg -d 'michael jordan'

    $ python -m facereg -d 'michael jordan' -l 5

* Recognition

.. code::

    # -i: Directory path for image

    $ python -m facereg -i tests/resources/michael_jordan.jpeg

Sample Result

=============

|image_sample|

.. |image_layers| image:: https://raw.githubusercontent.com/verifid/facereg/master/resources/layers.png

.. |image_sample| image:: https://raw.githubusercontent.com/verifid/facereg/master/resources/mj&sp.png