How dhanvina/facetrackedu works
• Face Capture & Camera Interface – This component interacts with the hardware (camera) to capture images to be processed.
• Face Detection Module – Using Haar Cascade (and possibly additional pre-processing) to locate the face within the captured images.
• Face Registration & Training Module – The registration (register.py) and training functions compile and label images; this is supported by files in the TrainingImageLabel directory and datasets.
• Face Recognition Module – Using algorithms such as LBPH (via predict.py) that compare incoming face data against the trained models.
• Attendance Management and Data Storage – Components that record and update attendance data using CSV/Excel files stored in directories like Attendance, facedetect (attendance.xlsx, dbdump01.csv, markedattendance.csv) and StudentDetails.
• User Interface / Execution Environment – Although no full GUI is seen, the command line/IDE operations (invoked via “py main.py” as mentioned in the README) serve as the application’s interface.
Relationships and Interactions
• A flow from the Camera Interface to the Face Detection Module.
• From detection, split into two parallel flows: one branch going to registration/training (for new face entries) and another leading to the recognition process for checking attendance.
• The Recognition Module then updates the Attendance Data Storage by marking the recognized faces.
• Additionally, visual feedback could be provided to the teacher through the IDE or a lightweight UI.
Architectural Patterns and Design Principles
• Modular Separation – The project clearly separates the face detection, registration, prediction, and attendance record management into distinct Python scripts and directories. Emphasize how each module has distinct responsibilities.
• Data Flow Design – The use of CSV/Excel files for both training labels and attendance records indicates a file-based data persistence mechanism.
• Integration of External Libraries – Note the dependency on external modules (OpenCV, Numpy, Pandas) that drive the recognition algorithms.
Relevant Technologies and Libraries
• Python 3 as the development language.
• OpenCV (with its contrib components) for image processing and face recognition.
• Numpy and Pandas for data manipulation and handling CSV/Excel records.
• Optional: Tools like PyCharm and VS Code for development, though these are less central to the architecture.