Cover Image

The effect of training data selection on face recognition in surveillance application

Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subj...

Full description

Saved in:
Bibliographic Details
Main Authors: Jamal Ahmad Dargham, Ali Chekima, Ervin Gubin Moung, Segiru Omatu
Format: Article
Language:English
English
Published: Springer 2015
Subjects:
QA71-90 Instruments and machines
Online Access:https://eprints.ums.edu.my/id/eprint/34962/1/FULL%20TEXT.pdf
https://eprints.ums.edu.my/id/eprint/34962/2/ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/34962/
https://link.springer.com/chapter/10.1007/978-3-319-19638-1_26
http://dx.doi.org/10.1007/978-3-319-19638-1_26
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ums.eprints.34962
record_format eprints
spelling my.ums.eprints.349622022-11-24T04:06:20Z https://eprints.ums.edu.my/id/eprint/34962/ The effect of training data selection on face recognition in surveillance application Jamal Ahmad Dargham Ali Chekima Ervin Gubin Moung Segiru Omatu QA71-90 Instruments and machines Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subject and the camera, distance class, the effect of the number of images per class, and also the effect of database used for training have been investigated. The images in the database were equally divided into three classes: CLOSE, MEDIUM, and FAR, according to the distance of the subject from the camera. It was found that using images from the FAR class for training gives better performance than using either the MEDIUM or the CLOSE class. In addition, it was also found that using one image from each class for training gives the same recognition performance as using three images from the FAR class for training. It was also found that as the number of images per class increases, the recognition performance also increases. Lastly, it was found that by using one image per class from all the available database sessions gives the best recognition performance. Springer 2015 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/34962/1/FULL%20TEXT.pdf text en https://eprints.ums.edu.my/id/eprint/34962/2/ABSTRACT.pdf Jamal Ahmad Dargham and Ali Chekima and Ervin Gubin Moung and Segiru Omatu (2015) The effect of training data selection on face recognition in surveillance application. Advances in Distributed Computing and Artificial Intelligence Journal, 373 (4). pp. 227-234. ISSN 2255-2863 https://link.springer.com/chapter/10.1007/978-3-319-19638-1_26 http://dx.doi.org/10.1007/978-3-319-19638-1_26
institution Universiti Malaysia Sabah
building UMS Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sabah
content_source UMS Institutional Repository
url_provider http://eprints.ums.edu.my/
language English
English
topic QA71-90 Instruments and machines
spellingShingle QA71-90 Instruments and machines
Jamal Ahmad Dargham
Ali Chekima
Ervin Gubin Moung
Segiru Omatu
The effect of training data selection on face recognition in surveillance application
description Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subject and the camera, distance class, the effect of the number of images per class, and also the effect of database used for training have been investigated. The images in the database were equally divided into three classes: CLOSE, MEDIUM, and FAR, according to the distance of the subject from the camera. It was found that using images from the FAR class for training gives better performance than using either the MEDIUM or the CLOSE class. In addition, it was also found that using one image from each class for training gives the same recognition performance as using three images from the FAR class for training. It was also found that as the number of images per class increases, the recognition performance also increases. Lastly, it was found that by using one image per class from all the available database sessions gives the best recognition performance.
format Article
author Jamal Ahmad Dargham
Ali Chekima
Ervin Gubin Moung
Segiru Omatu
author_facet Jamal Ahmad Dargham
Ali Chekima
Ervin Gubin Moung
Segiru Omatu
author_sort Jamal Ahmad Dargham
title The effect of training data selection on face recognition in surveillance application
title_short The effect of training data selection on face recognition in surveillance application
title_full The effect of training data selection on face recognition in surveillance application
title_fullStr The effect of training data selection on face recognition in surveillance application
title_full_unstemmed The effect of training data selection on face recognition in surveillance application
title_sort effect of training data selection on face recognition in surveillance application
publisher Springer
publishDate 2015
url https://eprints.ums.edu.my/id/eprint/34962/1/FULL%20TEXT.pdf
https://eprints.ums.edu.my/id/eprint/34962/2/ABSTRACT.pdf
https://eprints.ums.edu.my/id/eprint/34962/
https://link.springer.com/chapter/10.1007/978-3-319-19638-1_26
http://dx.doi.org/10.1007/978-3-319-19638-1_26
_version_ 1760231365462196224
score 13.211869

Similar Items