On the Use of a Low-Cost Embedded System for Face Detection and Recognition

Ramiro Sandoval; Vanessa Camino; Ricardo Flores Moyano; Daniel Riofrio; Noel Perez; Diego Benitez

doi:10.1109/ColCACI50549.2020.9247856

On the Use of a Low-Cost Embedded System for Face Detection and Recognition

Ramiro Sandoval
, Vanessa Camino
, Ricardo Flores Moyano
, Daniel Riofrio
, Noel Perez
, Diego Benitez

Universidad San Francisco de Quito

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper explores the feasibility of using commercially available off-the-shelf components to implement a low-cost embedded system as the core of a facial detection and recognition system. The system is composed of a Raspberry Pi camera module and a Raspberry Pi B+ enhanced by an Intel Neural Compute Stick 2. Four supervised learning models were implemented on the embedded system for face recognition under different conditions to determine the limitations and capabilities of the system, and the best operational conditions. Best results were achieved when using a Multilayer Perceptron (MLP) algorithm and the distance of the subject to the camera was between 0.3 to 1 meters, the illumination factor in the range from 115 to 130 lux and the horizontal face rotation between -5° to +5°.

Original language	English
Title of host publication	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings
Editors	Alvaro David Orjuela-Canon
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728194066
DOIs	https://doi.org/10.1109/ColCACI50549.2020.9247856
State	Published - 7 Aug 2020
Event	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Virtual, Cali, Colombia Duration: 7 Aug 2020 → 9 Aug 2020

Publication series

Name	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

Conference

Conference	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020
Country/Territory	Colombia
City	Virtual, Cali
Period	7/08/20 → 9/08/20

Keywords

Caffe
Intel neural stick 2
OpenFace
Raspberry pi 3 b+
embedded system
face detection
face recognition

Access to Document

10.1109/ColCACI50549.2020.9247856

Cite this

Sandoval, R., Camino, V., Moyano, R. F., Riofrio, D., Perez, N., & Benitez, D. (2020). On the Use of a Low-Cost Embedded System for Face Detection and Recognition. In A. D. Orjuela-Canon (Ed.), 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings Article 9247856 (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ColCACI50549.2020.9247856

Sandoval, Ramiro ; Camino, Vanessa ; Moyano, Ricardo Flores et al. / On the Use of a Low-Cost Embedded System for Face Detection and Recognition. 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. editor / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings).

@inproceedings{885a130217dc4c1d90d62887cc9c8c0b,

title = "On the Use of a Low-Cost Embedded System for Face Detection and Recognition",

abstract = "This paper explores the feasibility of using commercially available off-the-shelf components to implement a low-cost embedded system as the core of a facial detection and recognition system. The system is composed of a Raspberry Pi camera module and a Raspberry Pi B+ enhanced by an Intel Neural Compute Stick 2. Four supervised learning models were implemented on the embedded system for face recognition under different conditions to determine the limitations and capabilities of the system, and the best operational conditions. Best results were achieved when using a Multilayer Perceptron (MLP) algorithm and the distance of the subject to the camera was between 0.3 to 1 meters, the illumination factor in the range from 115 to 130 lux and the horizontal face rotation between -5° to +5°.",

keywords = "Caffe, Intel neural stick 2, OpenFace, Raspberry pi 3 b+, embedded system, face detection, face recognition",

author = "Ramiro Sandoval and Vanessa Camino and Moyano, \{Ricardo Flores\} and Daniel Riofrio and Noel Perez and Diego Benitez",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 ; Conference date: 07-08-2020 Through 09-08-2020",

year = "2020",

month = aug,

day = "7",

doi = "10.1109/ColCACI50549.2020.9247856",

language = "Ingl{\'e}s",

series = "2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Orjuela-Canon, \{Alvaro David\}",

booktitle = "2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings",

}

Sandoval, R, Camino, V, Moyano, RF , Riofrio, D , Perez, N & Benitez, D 2020, On the Use of a Low-Cost Embedded System for Face Detection and Recognition. in AD Orjuela-Canon (ed.), 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings., 9247856, 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020, Virtual, Cali, Colombia, 7/08/20. https://doi.org/10.1109/ColCACI50549.2020.9247856

On the Use of a Low-Cost Embedded System for Face Detection and Recognition. / Sandoval, Ramiro; Camino, Vanessa; Moyano, Ricardo Flores et al.
2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. ed. / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2020. 9247856 (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On the Use of a Low-Cost Embedded System for Face Detection and Recognition

AU - Sandoval, Ramiro

AU - Camino, Vanessa

AU - Moyano, Ricardo Flores

AU - Riofrio, Daniel

AU - Perez, Noel

AU - Benitez, Diego

PY - 2020/8/7

Y1 - 2020/8/7

N2 - This paper explores the feasibility of using commercially available off-the-shelf components to implement a low-cost embedded system as the core of a facial detection and recognition system. The system is composed of a Raspberry Pi camera module and a Raspberry Pi B+ enhanced by an Intel Neural Compute Stick 2. Four supervised learning models were implemented on the embedded system for face recognition under different conditions to determine the limitations and capabilities of the system, and the best operational conditions. Best results were achieved when using a Multilayer Perceptron (MLP) algorithm and the distance of the subject to the camera was between 0.3 to 1 meters, the illumination factor in the range from 115 to 130 lux and the horizontal face rotation between -5° to +5°.

AB - This paper explores the feasibility of using commercially available off-the-shelf components to implement a low-cost embedded system as the core of a facial detection and recognition system. The system is composed of a Raspberry Pi camera module and a Raspberry Pi B+ enhanced by an Intel Neural Compute Stick 2. Four supervised learning models were implemented on the embedded system for face recognition under different conditions to determine the limitations and capabilities of the system, and the best operational conditions. Best results were achieved when using a Multilayer Perceptron (MLP) algorithm and the distance of the subject to the camera was between 0.3 to 1 meters, the illumination factor in the range from 115 to 130 lux and the horizontal face rotation between -5° to +5°.

KW - Caffe

KW - Intel neural stick 2

KW - OpenFace

KW - Raspberry pi 3 b+

KW - embedded system

KW - face detection

KW - face recognition

UR - https://www.scopus.com/pages/publications/85097552466

U2 - 10.1109/ColCACI50549.2020.9247856

DO - 10.1109/ColCACI50549.2020.9247856

M3 - Contribución a la conferencia

AN - SCOPUS:85097552466

T3 - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

BT - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

A2 - Orjuela-Canon, Alvaro David

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020

Y2 - 7 August 2020 through 9 August 2020

ER -

Sandoval R, Camino V, Moyano RF , Riofrio D , Perez N , Benitez D. On the Use of a Low-Cost Embedded System for Face Detection and Recognition. In Orjuela-Canon AD, editor, 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9247856. (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings). doi: 10.1109/ColCACI50549.2020.9247856

On the Use of a Low-Cost Embedded System for Face Detection and Recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this