Offline facial recognition using machine learning techniques for examination attendance & logging

Author

Taonga, Bhebhe E.

Title

Offline facial recognition using machine learning techniques for examination attendance & logging

Abstract

This research project aimed to develop a machine learning-powered Android application for offline facial authentication of students during exams, attendance marking, and break logging. The mobile application is designed to capture and process facial features for subsequent recognition using a deep learning model. The proposed system comprises several processing stages, including image processing, feature extraction, and facial recognition. The facial recognition model integrated into the mobile application is based on a convolutional neural network (CNN) architecture trained on a large dataset of image samples.

Date

June 2024

Publisher

BUSE

Keywords

Machine learning-powered Android application,

Offline facial authentication,

Facial recognition model.

Supervisor

Mr. T. Mhlanganiso