Scribd
Upload
17 views13 pages

Face Recognition Attendance Modified

The document presents a Face Recognition-Based Attendance System aimed at automating attendance tracking to improve accuracy and reduce human error. It utilizes tools like Python, OpenCV, and MySQL, and follows a workflow that includes face detection, data collection, model training, and attendance logging. While the system offers advantages such as speed and scalability, it also faces challenges like sensitivity to lighting and privacy concerns.

Uploaded by

lathayh2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
17 views13 pages

Face Recognition Attendance Modified

The document presents a Face Recognition-Based Attendance System aimed at automating attendance tracking to improve accuracy and reduce human error. It utilizes tools like Python, OpenCV, and MySQL, and follows a workflow that includes face detection, data collection, model training, and attendance logging. While the system offers advantages such as speed and scalability, it also faces challenges like sensitivity to lighting and privacy concerns.

Uploaded by

lathayh2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

Face Recognition-Based

Attendance System
Presented by: Srushti D
USN: 4UB22EC060
UBDTCE
Introduction
• Manual attendance tracking is inefficient and
error-prone.
• This project utilizes face recognition to
automate the process.
• Improves accuracy, security, and reduces
human intervention.
Tools and Technologies Used
• Python, OpenCV, NumPy
• Haar Cascade Classifier for face detection
• LBPH algorithm for face recognition
• MySQL for database storage
• Flask for API integration
Workflow Overview
• 1. Face Detection
• 2. Data Collection
• 3. Model Training
• 4. Real-time Face Recognition
• 5. Attendance Logging
Face Detection
• Detects faces using Haar Cascade in real-time
video frames.
• Converts frame to grayscale before detection.
• Returns coordinates of detected faces.
Data Collection
• Captures 50–100 face images per individual.
• Images are labeled with unique user IDs.
• Images are stored in a dataset folder for
training.
Model Training
• Uses LBPH (Local Binary Pattern Histogram)
algorithm.
• Extracts features and creates histograms.
• Trains on labeled images and saves model for
recognition.
Face Recognition
• Real-time recognition using webcam input.
• Recognized face is compared with trained
model.
• Outputs user ID and confidence score.
Attendance Logging
• Marks attendance if confidence score is below
threshold.
• Logs timestamp and user info in MySQL
database.
• Prevents duplicate entries for the same
session.
Advantages
• Automated and fast attendance process.
• Eliminates proxy attendance.
• Low-cost setup with high scalability.
• Environmentally friendly and reduces
paperwork.
Disadvantages
• Sensitive to lighting and face angle.
• Masks or accessories can affect recognition.
• Requires retraining for major facial changes.
• Raises privacy concerns.
Future Scope
• Implement deep learning models for better
accuracy.
• Develop a mobile app for remote attendance.
• Cloud integration for centralized storage.
• Support for masked face detection and
emotion analysis.
Conclusion
• A robust system to automate attendance using
face recognition.
• Combines computer vision with database
logging.
• Improves efficiency and reliability over manual
methods.
• Potential for further development and
integration.

You might also like