Small face detection using deep learning on surveillance videos

Rolando J. Cárdenas; Cesar A. Beltrán; Juan Carlos Gutierrez Caceres

doi:10.18178/ijmlc.2019.9.2.785

Small face detection using deep learning on surveillance videos

Rolando J. Cárdenas, Cesar A. Beltrán, Juan Carlos Gutierrez Caceres

Departamento Académico de Ingeniería de Sistemas e Informática

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Face detection is one of the essential tasks widely studied in the field of Computer Vision. Several authors have developed different techniques to improve the face detection in images, but these are limited in their application on videos and more if they present low resolution. In this study, we propose a new model for face detection in low-resolution videos based on the morphology of the upper body of people, and the use of Deep Learning (CNN). Our results show an average of 39% accuracy over the Caviar dataset and 32% in the UCSP dataset. Compared with other techniques, our results are greater due they only reach 1% of accuracy.

Original language	English
Pages (from-to)	189-194
Number of pages	6
Journal	International Journal of Machine Learning and Computing
Volume	9
Issue number	2
DOIs	https://doi.org/10.18178/ijmlc.2019.9.2.785
State	Published - 1 Apr 2019

Bibliographical note

Funding Information:
This research was supported by CIENCIACTIVA, CONCYTEC, and the National University of San Agustin (UNSA). The authors thank all the professors who collaborated in this research.

Publisher Copyright:
© 2019, International Association of Computer Science and Information Technology.

Keywords

Deep learning
Face detection
Low resolution
Video

Access to Document

10.18178/ijmlc.2019.9.2.785

Cite this

@article{1bbbc8e258b045268e84478b4f2fb32b,

title = "Small face detection using deep learning on surveillance videos",

abstract = "Face detection is one of the essential tasks widely studied in the field of Computer Vision. Several authors have developed different techniques to improve the face detection in images, but these are limited in their application on videos and more if they present low resolution. In this study, we propose a new model for face detection in low-resolution videos based on the morphology of the upper body of people, and the use of Deep Learning (CNN). Our results show an average of 39% accuracy over the Caviar dataset and 32% in the UCSP dataset. Compared with other techniques, our results are greater due they only reach 1% of accuracy.",

keywords = "Deep learning, Face detection, Low resolution, Video",

author = "C{\'a}rdenas, {Rolando J.} and Beltr{\'a}n, {Cesar A.} and {Gutierrez Caceres}, {Juan Carlos}",

note = "Publisher Copyright: {\textcopyright} 2019, International Association of Computer Science and Information Technology.",

year = "2019",

month = apr,

day = "1",

doi = "10.18178/ijmlc.2019.9.2.785",

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

volume = "9",

pages = "189--194",

journal = "International Journal of Machine Learning and Computing",

issn = "2010-3700",

publisher = "International Association of Computer Science and Information Technology",

number = "2",

}

TY - JOUR

T1 - Small face detection using deep learning on surveillance videos

AU - Cárdenas, Rolando J.

AU - Beltrán, Cesar A.

AU - Gutierrez Caceres, Juan Carlos

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Face detection is one of the essential tasks widely studied in the field of Computer Vision. Several authors have developed different techniques to improve the face detection in images, but these are limited in their application on videos and more if they present low resolution. In this study, we propose a new model for face detection in low-resolution videos based on the morphology of the upper body of people, and the use of Deep Learning (CNN). Our results show an average of 39% accuracy over the Caviar dataset and 32% in the UCSP dataset. Compared with other techniques, our results are greater due they only reach 1% of accuracy.

AB - Face detection is one of the essential tasks widely studied in the field of Computer Vision. Several authors have developed different techniques to improve the face detection in images, but these are limited in their application on videos and more if they present low resolution. In this study, we propose a new model for face detection in low-resolution videos based on the morphology of the upper body of people, and the use of Deep Learning (CNN). Our results show an average of 39% accuracy over the Caviar dataset and 32% in the UCSP dataset. Compared with other techniques, our results are greater due they only reach 1% of accuracy.

KW - Deep learning

KW - Face detection

KW - Low resolution

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=85064974600&partnerID=8YFLogxK

U2 - 10.18178/ijmlc.2019.9.2.785

DO - 10.18178/ijmlc.2019.9.2.785

M3 - Artículo

AN - SCOPUS:85064974600

VL - 9

SP - 189

EP - 194

JO - International Journal of Machine Learning and Computing

JF - International Journal of Machine Learning and Computing

SN - 2010-3700

IS - 2

ER -

Small face detection using deep learning on surveillance videos

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this