SINGHxTUSHAR / AutoMark

This is a Smart Attendance System designed using a pre-trained model called Haar-Cascade Classifier, OpenCV and other various Dependencies to mark the attendance in a smarter way and saves the lecture time.

AutoMark 🙋🏻‍♂️📋:

AutoMark is a smart Attendance system that uses the OpenCV and Haar-Cascade Classifier to mark the attendance of the students.

This project implements a smart attendance system for students using OpenCV (Open Source Computer Vision Library) and a pre-trained Haar cascade classifier. Here's a breakdown of the functionalities:

System Components:

• Camera: Captures real-time video feed of the students.
• OpenCV Libraries: Used for image processing tasks like frame grabbing, face detection, and drawing bounding boxes.
• Haar Cascade Classifier: A pre-trained model that efficiently detects frontal human faces within the video frames.
• Student Database: Stores student information like IDs, names, and potentially facial images (optional for enhanced recognition).
• Attendance Marking System: Logs attendance data, typically with timestamps and student IDs. This can be a simple text file, a spreadsheet, or integrated with existing attendance management software.

Working Process:

• Real-time Video Capture: The system continuously captures video frames from the camera.
• Face Detection: OpenCV utilizes the Haar cascade classifier to identify and locate faces within each frame.
• Student Recognition (Optional): If the system stores student facial data, additional algorithms (not necessarily Haar cascade) might be used to recognize specific students within the detected faces.
• Attendance Marking: Based on detected faces (and potentially recognized students), the system marks attendance in the database. This might involve recording timestamps and student IDs (or names).
• Visualization (Optional): The system can display the video feed with bounding boxes around the detected faces for real-time monitoring purposes.

Benefits:

• Automated Attendance: Eliminates the need for manual attendance checks, saving time and reducing errors.
• Scalability: The system can handle multiple students simultaneously.
• Reduced Contact (Optional): If facial recognition is implemented, students might not need to physically interact with a device to register attendance.
• Cost-effective: Leverages open-source libraries like OpenCV, making it a budget-friendly solution.

Limitations:

• Haar cascade limitations: The pre-trained model might struggle with angled faces, poor lighting conditions, or occlusions (e.g., hats, masks).
• Privacy Concerns: Storing student facial data raises privacy considerations that need to be addressed with proper security measures and user consent.

Commands ✍️:

• This will be used to add face to dataset and face will be recorded via webcam.

python Add_faces.py

• Record attendance of added face , press 'o' to record attendance and it will create csv file corresponding to date present , name and timestamp will be recorded.

python test.py

• Attendance will be displayed here and can be downloaded in csv format.

streamlit run app.py

Output 📁:

For more output images visit: Link

Reference 🧧:

• Classifier Documentation
• Streamlit Documentation
• Research Paper Documentation

Requirements💻 :

Ensure you have the following dependencies installed:

• Python (version 3.9.x || 3.12.x)
• IDE: VS-CODE or collab
• Virtual-environment(venv)
• Other dependencies (refer to the requirements.txt)

You can install the required Python packages using:

pip install -r requirements.txt

Setup 💿:

• Clone the repository:

git clone https://github.com/SINGHxTUSHAR/AutoMark.git
cd AutoMark

• Create a virtual environment (optional but recommended):

python -m venv venv

• Activate the virtual environment:
  • On Windows:

  venv\Scripts\activate

  • On macOS/Linux:

  source venv/bin/activate

Contributing 📌:

If you'd like to contribute to this project, please follow the standard GitHub fork and pull request process. Contributions, issues, and feature requests are welcome!

Suggestion 🚀:

If you have any suggestions for me related to this project, feel free to contact me at [e-mail] or LinkedIn.

License 📝:

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