Facial recognition security alert system

Gabriela Da Silva Sousa, Elie Ngomseu Mambou, Theo G. Swart

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

In this paper the design and implementation of a real-time face recognition security system is presented. The security system demonstrates how surveillance can be adapted to offer a greater level of security with facial recognition. The security system was implemented in a four-person household. Results show that the designed facial recognition security system achieved a 100% training and 96% validation accuracy with a 100% accuracy on the test images dataset consisting of unseen images of the four enrolled users.

Original languageEnglish
Title of host publicationProceedings of 2021 IEEE AFRICON, AFRICON 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665419840
DOIs
Publication statusPublished - 13 Sept 2021
Event2021 IEEE AFRICON, AFRICON 2021 - Virtual, Arusha, Tanzania, United Republic of
Duration: 13 Sept 202115 Sept 2021

Publication series

NameIEEE AFRICON Conference
Volume2021-September
ISSN (Print)2153-0025
ISSN (Electronic)2153-0033

Conference

Conference2021 IEEE AFRICON, AFRICON 2021
Country/TerritoryTanzania, United Republic of
CityVirtual, Arusha
Period13/09/2115/09/21

Keywords

  • Face recognition
  • Raspberry Pi
  • Security
  • Transfer learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Facial recognition security alert system'. Together they form a unique fingerprint.

Cite this