FaceApproval - Facial Recognition + Attendance System

A simple facial recognition attendance system demo built with React, FastAPI, and OpenCV LBPH.

---

Features

• Dual Enrollment - Webcam or file upload
• Real-time Recognition - Automatic attendance marking
• Live Dashboard - Stats and records
• Google Sheets - Auto data sync
• Responsive - Works on all devices

---

Tech Stack

Frontend: React, Tailwind CSS, React Webcam
Backend: FastAPI, OpenCV (LBPH), Google Sheets API
Algorithm: LBPH (Local Binary Patterns Histograms)

---

🚀 Quick Start

Prerequisites

• Python 3.11+
• Node.js 16+
• Google Sheets API credentials

Setup

Backend:

cd backend
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
python -m uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Frontend:

cd frontend
npm install
npm start

Access: http://localhost:3000

Google Sheets Setup

• put the google_sheets_creds.json file(downloaded from https://console.cloud.google.com) and store it in a credentials folder in the backend directory and add the required path and spreadsheet ID from google sheets also share the spreadsheet with the service account email created Procedure
  • Click "New Project" → add project name and → Create
  • Enable Google Sheets API from library
  • from API & services -> create credentials -> Service Account and grant editor access after creation
  • from the service account create key in JSON format and create(automatic download to system)

Usage

1. Enroll - Capture or upload face photo
2. Approve Entry - Face camera for recognition
3. Dashboard - View attendance stats

---

Structure

├── backend/          # FastAPI + OpenCV
│   ├── app/
│   ├── data/
│   └── credentials/
└── frontend/         # React UI
    └── src/

---

API Endpoints

• POST /api/enroll/webcam - Enroll from camera
• POST /api/enroll/file - Enroll from file
• POST /api/approve - Mark attendance
• GET /api/dashboard/stats - Get statistics

API Docs: http://localhost:8000/docs

---

Mechanism

Uses LBPH algorithm for face recognition:

• Detects faces with Haar Cascade
• Extracts texture patterns
• Trains on each enrollment
• Recognizes faces in real-time

---

⭐ Demo project for my learning purposes