Scribd
Upload
7 views

Project Documentation

Uploaded by

deepucchembra
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
7 views

Project Documentation

Uploaded by

deepucchembra
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

# Face Recognition Web Application Documentation

## Project Overview

This Django-based web application implements a face recognition system. It allows


users to register faces, train the recognition model, and perform face predictions.

### Key Features

1. Face Registration: Capture multiple images of a person's face using a camera.


2. Model Training: Generate face embeddings and train a classification model.
3. Face Prediction: Detect and recognize faces in new images or video streams.

## Project Structure

```
face_recognition_web/
├── face_app/
│ ├── migrations/
│ ├── templates/
│ │ └── face_app/
│ │ ├── base.html
│ │ ├── home.html
│ │ ├── register.html
│ │ ├── train.html
│ │ ├── predict.html
│ │ └── predict_result.html
│ ├── __init__.py
│ ├── admin.py
│ ├── apps.py
│ ├── consumers.py
│ ├── face_model.py
│ ├── facePredictor.py
│ ├── face_preprocess.py
│ ├── faces_embedding.py
│ ├── forms.py
│ ├── get_faces_from_camera.py
│ ├── helper.py
│ ├── models.py
│ ├── mtcnn_detector.py
│ ├── routing.py
│ ├── softmax.py
│ ├── train_softmax.py
│ ├── urls.py
│ └── views.py
├── face_recognition_web/
│ ├── __init__.py
│ ├── asgi.py
│ ├── settings.py
│ ├── urls.py
│ └── wsgi.py
├── media/
│ ├── uploads/
│ └── temp/
├── static/
└── manage.py
```

## Key Components
1. `views.py`: Contains the main logic for handling HTTP requests.
2. `facePredictor.py`: Implements face detection and recognition.
3. `get_faces_from_camera.py`: Collects face images for registration.
4. `faces_embedding.py`: Generates face embeddings for training.
5. `train_softmax.py`: Trains the face recognition model.
6. `consumers.py`: Handles WebSocket connections for real-time predictions.

## Setup and Installation

1. Clone the repository


2. Install dependencies: `pip install -r requirements.txt`
3. Apply migrations: `python manage.py migrate`
4. Run the server: `python manage.py runserver`

## Usage

1. Access the home page


2. Register new faces using the "Register" page
3. Train the model using the "Train" page
4. Perform face recognition using the "Predict" page

## API Endpoints

- `/`: Home page


- `/register/`: Face registration page
- `/train/`: Model training page
- `/predict/`: Face prediction page

## WebSocket

- `ws/predict/`: WebSocket endpoint for real-time predictions

## Future Improvements

- Implement user authentication


- Optimize face detection and recognition for better performance
- Add periodic model retraining
- Implement batch processing for large datasets

You might also like