Face Log TZ

Abstract

1. Introduction

Traditional attendance tracking in schools is manual, slow, and prone to errors. FaceLogTZ modernizes classroom management by using AI to identify students in real-time and automatically log their presence.

A modern, multithreaded Computer Vision system that automates classroom attendance using advanced facial recognition, real-time audio queues, and instant WhatsApp cloud notifications.

Designed specifically with local African environments in mind, this system operates on a Hybrid Edge-to-Cloud architecture. Heavy video processing and facial recognition happen entirely locally on the host machine to save bandwidth, while lightweight data is pushed securely to the cloud (Twilio) to instantly notify parents and stakeholders via WhatsApp.

2. Objective

FaceLogTZ: A simple face recognition attendance system built in Tanzania, applicable globally.

This project demonstrates how Python can be applied to a real-world AI & Machine Learning problem.

3. Key Features / Modules

• Modern Enterprise Dashboard: Built with customtkinter for a sleek, responsive, dark-mode user interface.
• Real-Time Cloud Notifications: Integrates with the Twilio API to automatically send WhatsApp delivery receipts to parents or managers the second a face is recognized.
• Smart Daily Validation: Date-aware logic ensures students are only logged once per day, preventing duplicate entries in the database.
• Asynchronous Audio Engine: A custom threading queue (pyttsx3) greets users by name one-by-one, preventing overlapping robotic voices or UI crashes during high-traffic moments.
• Robust Recognition Engine: Utilizes dynamic folder-scanning to learn multiple angles and lighting conditions for a single identity, increasing match accuracy across different skin tones.
• Hardware Optimized: Incorporates dynamic frame resizing (processing frames at 25% scale) to run smoothly even on older, low-resource school computers.

4. Technology Stack

• Core: Python 3.9+
• Computer Vision: OpenCV (cv2), face_recognition (128-dimension facial encodings)
• GUI: customtkinter, Pillow
• Cloud API: twilio (WhatsApp integration)
• Utilities: pyttsx3 (Text-to-Speech), python-dotenv (Security), threading, queue, NumPy

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/jemmziray-tech/FaceLogTZ.git
cd FaceLogTZ

git clone [https://github.com/jemmziray-tech/FaceLogTZ.git](https://github.com/jemmziray-tech/FaceLogTZ.git)
cd FaceLogTZ

pip install opencv-python face_recognition customtkinter twilio python-dotenv pyttsx3 Pillow numpy

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by jemmziray-tech and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.