haiderabasi / opencv-secure-access Goto Github PK

This is a Python-based secure access system that uses facial recognition and tracking to authenticate authorized personnel.

• Only allow device/premises access 🔓 to authorized individuals.

• Annoy 😠 kids away by disrupting their mouse/keyboard commands.

• Lockout crucial files/folders 🚫 from specified individuals.

(To-do) - Gather complete activity-data for selected users.

To run this project, you need to have the following Python packages installed:

• For Ubuntu

  • Install python 3.8 using the following steps (Ref)

    sudo add-apt-repository ppa:deadsnakes/ppa -y
    sudo apt install python3.8
    sudo apt install python3.8-distutils
    sudo apt install python3.8-dev
    sudo apt install python3.8-tk

  • Setup and activate virtual environment inside the repository

    sudo apt install pip -y
    python3 -m pip install --user virtualenv
    python3 -m virtualenv sa_venv -p /usr/bin/python3.8
    source sa_venv/bin/activate

  • Install required modules using the following two commands.

    pip install -r prequirements.txt
    pip install -r requirements.txt

  • Test the application by running core.py

• For Windows 10

  • Download and install Python 3.8.10.- x64

    • Link

  • Setup a virtual environment and activate it inside the repository.

    python -m pip install --user virtualenv
    python -m virtualenv sa_venv -p C:/Users/cripplegen/AppData/Local/Programs/Python/Python38/python.exe
    cd .\sa_venv\Scripts\
    activate

  • You can install required packages by running the following command:

    pip install -r win_requirements.txt

  • Select the virutal environment Python in VScode

  • Run core.py (Use config.py to switch between debug/live)

To activate the secure access system, call the activate_sa method of the secure_access_cv class with the following arguments:

• vid_id: The ID of the camera/webcam device to capture frames from or the path of the video file to use.
• dataset_dir: The path to the directory containing the folders of image/s of authorized personnel to use for training the face recognition model.

Here's an example:

from core import secure_access_cv

sas = secure_access_cv()
sas.activate_sa(vid_id=0, dataset_dir="authorized_personnels")

The main file of the secure access system is core.py, which contains the secure_access_cv class.

|
+──authorized_personnels > (Authorized personnel images)
│   ├──Person #1 > (folder storing image/s of person 1)
│   └──Person #2
| 
|──data > data folder containing test images and video for debugging
│  └──test
|
+──models  > (Detection + Recognition + Embeddings)
│  ├──dlib_face_recognition_resnet_model_v1.dat
│  ├──known-live_embeddings-face_enc
│  ├──mmod_human_face_detector.dat
│  ├──shape_predictor_5_face_landmarks.dat
│  └──shape_predictor_68_face_landmarks.dat
|
├──.gitignore
├──LICENSE
|
|──config.py > (control variables for secure access)
├──tree.MD
|
|──requirements.txt > (required modules to run)
├──core.spec > (File for pyinstaller to generate executable for app)
|
+──core.py    > (Main file to run Secure Access App)
├──multi_object_tracking.py
├──recognition.py
└──utilities.py

# 1) Install pyinstaller module
pip install --upgrade pyinstaller

# 2) Configure core.spec according to your requirements

# 3) Create executable using pyinstaller
pyinstaller .\core.spec

If you'd like to contribute to this project, please fork the repository and make a pull request.

This project is licensed under the MIT License - see the LICENSE file for details.

Thank you 👏 ageitgey.

Your work has made using face recognition in projects a walk in the park.

Also, thanks to Davis King (@nulhom) for creating dlib and for providing the trained facial feature detection and face encoding models used in this library.

Keep the OpenSource torch lit! 🔥