Tools
Tools
-, Rajiv (2022) Improving the Face Recognition capabilities using DenseNet architecture for Attendance management system in Cloud Computing Environment. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (784kB) | Preview |
Preview |
PDF (Configuration manual)
Download (985kB) | Preview |
Abstract
In the educational institutions, managing the attendance of student and staff is a tedious task. The traditional approach of attendance system is manual, time consuming and may contain fallacies in the record due to human mistake. Therefore, in order to resolve such issues in this work we have proposed a framework for attendance management system. which can automatically detect the person based on captured face data. As a onetime process, student needs to register themselves by providing their name and capture their image. The captured image will be trained on the deep learning model and next time the model will be able to detect the trained face. In this work we have used 3 different deep learning architectures that are VGG-19, ResNet-50 and DenseNet model. After comparative analysis, we have obtained better results using DenseNet architecture where Facenet and MTCNN has been used to localize the face from video and extract the face features.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Cloud Computing |
| Depositing User: | Tamara Malone |
| Date Deposited: | 02 Dec 2022 17:49 |
| Last Modified: | 07 Mar 2023 16:17 |
| URI: | https://norma.ncirl.ie/id/eprint/5962 |
Actions (login required)
 |
View Item |