In this chapter, we present a compilation of applications developed during our internship. Focusing on digital projects, we chose to delve into Deep Learning-based object detection—a critical and evolving field in today's technological landscape. At the outset of the project, we received code written in Python, a language with which we had limited familiarity, leveraging the OpenCV library for computer vision, which was entirely new to us.
Introduction: Facial recognition integrates biometric techniques, artificial intelligence, 3D mapping, and Deep Learning to compare and analyze facial features for identification purposes.
Application: We aimed to develop a simple yet effective face authentication system as a desktop application for automated absence management, leveraging complex machine learning algorithms and image processing.
User Interface: The graphical interface acts as a gateway to access various functionalities, featuring buttons for dataset collection, model training, and launching the automated absence application.
Dataset Collection: Users can collect student data by capturing 30 images per student, stored in individual directories named after each student.
Model Training: Training the model involves a straightforward process, where clicking "Train the Model" initiates and completes the training in seconds.
Usage: Once trained, clicking "Run" launches the application to automate absence reporting. After a specified time, the application closes and sends a CSV file via Gmail to the teacher, listing present students along with their attendance times.
GitHub Repository: The project is publicly accessible on GitHub, providing comprehensive documentation and access to the codebase.
This initiative showcases our proficiency in leveraging cutting-edge technologies to address practical challenges in digital applications, highlighting our competence in Python programming, OpenCV integration, and advanced AI techniques for real-world solutions.