Person Recognition for Access Logging

Authors

Andrew Boka, University of California, Berkeley
Brendan Morris, University of Nevada, Las VegasFollow

Document Type

Conference Proceeding

Publication Date

3-14-2019

Publication Title

2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)

Publisher

EDAS

First page number:

933

Last page number:

936

Abstract

The goal of this project is to develop a complete hardware and software system for access monitoring into a secured facility using modern facial recognition technology (FRT) and lightweight, inexpensive components. FRT detects and recognizes individuals as they enter and exit the secured area, providing accessible logs for a visualization of this activity. The project uses FaceNet FRT which takes a deep-learning approach to increase facial recognition accuracy. With input from two portable cameras, the FaceNet FRT is implemented on a Raspberry Pi using the Intel Movidius Neural Compute system.

Keywords

Access monitoring; Facial recognition technology; Deep learning; Raspberry pi; Movidius neural compute stick

Disciplines

Computer Engineering | Computer Sciences | Engineering | Hardware Systems | Physical Sciences and Mathematics | Software Engineering

Language

English

Repository Citation

Boka, A., Morris, B. (2019). Person Recognition for Access Logging. 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC) 933-936. EDAS.
http://dx.doi.org/10.1109/CCWC.2019.8666483