The Zidio Face Recognition-Based Attendance System automates attendance tracking through facial recognition, eliminating the need for manual entry. This system aims to streamline the attendance process by reducing time and enhancing accuracy, making it suitable for educational institutions, workplaces, and other environments requiring regular attendance tracking.
This project implements a face data collection and storage system that uses OpenCV to detect faces in real-time via a webcam. The collected face data is then serialized and stored for future training and recognition purposes. By repeatedly capturing facial images of individuals, this system enables face recognition applications such as attendance monitoring.
This project is an extension of a facial recognition attendance system, utilizing machine learning and computer vision. It employs a K-Nearest Neighbors (KNN) classifier trained on facial images to automate attendance logging. The system can identify individuals in real time and log their attendance, including timestamped records stored in a CSV file, with text to-speech confirmation for a user-friendly experience.
This project uses Streamlit to create a dynamic attendance display application. It reads attendance data from a CSV file, which is updated periodically to showcase the latest attendance records in real time. The application uses st_autorefresh to automatically refresh the display at specified intervals, ensuring continuous updates. The project also includes a FizzBuzz counter example to demonstrate Streamlit’s auto-refresh functionality.