NORMA eResearch @NCI Library

Detection of Unauthorised Person in a Restricted Place using Deep Learning Algorithms

Said, Mayur Ishwar (2023) Detection of Unauthorised Person in a Restricted Place using Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (961kB) | Preview

Abstract

Security has always been a concern for everyone. Especially, in some highly volatile restricted places where only authorised individuals are allowed to enter. If some unauthorised individual breaches the security of such locations, he/she can cause catastrophic damage, potentially endangering people’s lives as well. In this research paper, a solution is proposed using a face detection algorithm(MTCNN) and a face recognition algorithm(VGGFace2) to identify an unauthorised person in a restricted place using its video footage only. The proposed solution is implemented and evaluated by carrying out several experiments using video clips on YouTube. The results of these experiments showed that MTCNN along with a pre-trained VGGFace 2 model gives the best performance with precision, recall, and f1-score of 0.872, 0.975, and 0.921 respectively.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Ul Ain, Qurrat
UNSPECIFIED
Subjects: H Social Sciences > HV Social pathology. Social and public welfare
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 25 May 2023 14:41
Last Modified: 25 May 2023 14:41
URI: https://norma.ncirl.ie/id/eprint/6645

Actions (login required)

View Item View Item