Face Attendance System

A Spring Boot-based face recognition attendance system that uses OpenCV and JavaCV for real-time face detection and recognition. The system can mark attendance through camera capture or uploaded images.

🚀 Features

• Real-time Face Recognition: Mark attendance using live camera feed
• Image Upload Support: Upload images for attendance marking
• Training System: Capture and train face recognition models
• Database Integration: Store attendance records in MySQL/H2 database
• Menu Image Management: Upload and view menu images per user
• RESTful API: Complete REST API for all operations

🛠️ Technology Stack

• Backend: Spring Boot 3.2.4
• Java Version: Java 17
• Computer Vision: OpenCV 4.7.0 with JavaCV 1.5.9
• Database: MySQL (production) / H2 (development)
• Face Recognition: LBPH (Local Binary Patterns Histograms) Face Recognizer
• Face Detection: Haar Cascade Classifier
• Build Tool: Maven

📋 Prerequisites

• Java 17 or higher
• Maven 3.6+
• MySQL 8.0+ (for production)
• Webcam (for camera-based attendance)
• Git

🔧 Installation & Setup

1. Clone the Repository

git clone <repository-url>
cd FaceAttendanceSystem

2. Database Setup

Create a MySQL database named faceattendance:

CREATE DATABASE faceattendance;

3. Configuration

Update src/main/resources/application.properties with your database credentials:

spring.datasource.url=jdbc:mysql://localhost:3306/faceattendance
spring.datasource.username=your_username
spring.datasource.password=your_password

4. Build and Run

# Build the project
mvn clean install

# Run the application
mvn spring-boot:run

The application will start on http://localhost:8080

📚 API Documentation

Face Recognition Endpoints

1. Capture Training Images

GET /api/face/capture/{userId}/{numImages}

Captures training images for a specific user.

• userId: User ID (1, 2, 3)
• numImages: Number of images to capture

Example: GET /api/face/capture/1/10

2. Train Model

GET /api/face/train

Trains the face recognition model using captured images.

3. Mark Attendance (Camera)

GET /api/face/mark-attendance

Marks attendance using live camera feed.

4. Mark Attendance (Image Upload)

POST /api/face/mark-attendance-from-image
Content-Type: multipart/form-data

image: [image file]

Marks attendance from an uploaded image.

5. Upload Menu Image

POST /api/face/upload-menu-image/{userId}
Content-Type: multipart/form-data

menuImage: [image file]

Uploads a menu image for a specific user.

6. View Menu Image

GET /api/face/menu-images/{userId}/view/{imageName}

Views a specific menu image for a user.

7. Clear Training Images

GET /api/face/clear-images/{userId}

Clears all training images for a specific user.

👥 User Management

The system currently supports 3 predefined users:

• User ID 1: Anurag Singh
• User ID 2: Rohit Singh
• User ID 3: Virat Kohli

📁 Project Structure

src/
├── main/
│   ├── java/com/org/
│   │   ├── controller/
│   │   │   └── FaceController.java          # REST API endpoints
│   │   ├── service/
│   │   │   └── FaceService.java            # Face recognition logic
│   │   ├── model/
│   │   │   └── Attendance.java             # Attendance entity
│   │   ├── repository/
│   │   │   └── AttendanceRepository.java    # Data access layer
│   │   └── FaceAttendanceSystemApplication.java
│   └── resources/
│       ├── application.properties          # Configuration
│       ├── haarcascade_frontalface_alt.xml # Face detection model
│       └── trained_faces/
│           └── lbph_model.xml             # Trained face recognition model

🔄 Workflow

1. Initial Setup

1. Start the application
2. Capture training images for each user using /api/face/capture/{userId}/{numImages}
3. Train the model using /api/face/train

2. Marking Attendance

• Camera Method: Use /api/face/mark-attendance for real-time attendance
• Image Method: Upload an image using /api/face/mark-attendance-from-image

3. Management

• Upload menu images using /api/face/upload-menu-image/{userId}
• View menu images using /api/face/menu-images/{userId}/view/{imageName}
• Clear training data using /api/face/clear-images/{userId}

📊 Database Schema

Attendance Table

CREATE TABLE attendance (
    id BIGINT AUTO_INCREMENT PRIMARY KEY,
    user_id INT NOT NULL,
    date DATE NOT NULL,
    time TIME NOT NULL,
    UNIQUE KEY unique_user_date (user_id, date)
);

🎯 Key Features Explained

Face Recognition Algorithm

• Uses LBPH (Local Binary Patterns Histograms) for face recognition
• Haar Cascade Classifier for face detection
• Confidence threshold: < 98.0 for camera, < 80 for images
• Face images resized to 160x160 pixels for consistency

File Storage

• Training images: C:/training_images/user{userId}/
• Menu images: C:/menu_images/user{userId}/
• Model file: src/main/resources/trained_faces/lbph_model.xml

Attendance Logic

• One attendance record per user per day
• Automatic duplicate prevention
• Timestamp tracking for each attendance

🚨 Troubleshooting

Common Issues

1. Camera Access Error

   • Ensure webcam is connected and not used by other applications
   • Check camera permissions

2. Model Not Found Error

   • Train the model first using /api/face/train
   • Ensure training images exist in C:/training_images/

3. Database Connection Error

   • Verify MySQL is running
   • Check database credentials in application.properties
   • Ensure database faceattendance exists

4. Face Not Recognized

   • Ensure sufficient training images (recommended: 10-20 per user)
   • Check lighting conditions
   • Verify face is clearly visible and frontal

🔒 Security Considerations

• The system stores images locally on the server
• Consider implementing authentication for production use
• Add input validation for file uploads
• Implement proper error handling and logging

🚀 Future Enhancements

• Web-based UI for easier interaction
• User authentication and authorization
• Attendance reports and analytics
• Multi-face detection support
• Cloud storage integration
• Mobile app support
• Real-time notifications
• Advanced face recognition models (Deep Learning)

📝 License

This project is licensed under the MIT License.

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

📞 Support

For support and questions, please open an issue in the repository.

---

Note: This system requires a webcam for camera-based attendance marking. Ensure your system has proper camera access permissions.