How codemisba/attendance-management-system_p2 works
Project Type and Purpose
• This is a desktop‑based Face Recognition Attendance Management System. It uses a Tkinter GUI for user interaction, OpenCV for computer vision (face detection + recognition), and CSV files (and potentially an SQL database) for data persistence. The primary use cases are adding/updating/deleting student records, training a face recognition model, and marking attendance via live camera feed.
File Structure
• Top‑level scripts:
• main.py – orchestrates the GUI and ties together the face recognition, data management, and attendance marking flows.
• mini_app.py – a streamlined version of the interface, likely a proof‑of‑concept or simplified front end.
• Test_Camera_Functionality.py – standalone module for verifying camera capture and face detection pipeline.
• Train_Images_By_Haarcascade.py – handles creation of training images from live feed and triggers model training.
• Data directories:
• Training_Images – raw face snapshots labeled per student.
• Training_Image_Label/trainner.yml – serialized trained face recognition model.
• Snapshots – runtime captures for debugging/verification.
• StudentDetails/StudentDetails.csv – master student database (ID, name, …).
• ManualAttendance/attendance.csv & SmartAttendance/*.csv – logs of attendance, separated by manual vs. automatic flows.
• Configuration/Resources:
• haarcascade_frontalface_default.xml – OpenCV cascade for face detection.
• Jupyter notebooks for hyperparameter tuning and experimentation (not part of the production pipeline).
README for Additional Insights
• Frameworks/Libraries: Python 3.7+, OpenCV, NumPy, Pandas, Tkinter.
• Data stores: CSV (with plans to move to SQL).
• Core features: real‑time face detection & recognition, timestamped attendance logging, student record CRUD.
Detail
• Directories and files that play a role in the runtime path: Training_Images, trainner.yml, haarcascade_frontalface_default.xml, StudentDetails.csv, attendance CSVs.
• Do not over‑abstract—show both ManualAttendance and SmartAttendance modules as separate logging sinks.
• Configuration files or parameters (e.g., hyperparameter notebooks) as side‑notes or footnotes.