A comparison of the YCBCR color space with gray scale for face recognition for surveillance applications

Jamal Ahmad Dargham, and Ali Chekima, and Ervin Gubin Moung, and Segiru Omatu, and Ali Semalat, and Grzegorz Bocewicz, and Paweł Sitek, and Izabela E. Nielsen, and Julián A. García García, and Javier Bajo, (2016) A comparison of the YCBCR color space with gray scale for face recognition for surveillance applications. Distributed Computing and Artificial Intelligence, 13th International Conference (Part I). pp. 203-211. ISSN 978-3-319-40161-4


Download (44kB) | Preview


Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In this paper, the performance of the individual channels from the YCBCR color space on face recognition for surveillance applications is investigated and compared with the performance of the gray scale. In addition, the performance of fusing two or more color channels is also compared with that of the gray scale. Three cases with different number of training images per persons were used as a test bed. It was found out that, the gray scale always outperforms the individual channel. However, the fusion of CBxCR with any other channel outperforms the gray scale when three images of the same class from the same database are used for training. The CBxCR channel gave the best performance for the individual color channels followed by CB, CB-CR, CB/CR and CR respectively. It was also found that, in general, increasing the number of fused channels in-creases the performance of the system.

Item Type: Article
Uncontrolled Keywords: Principal Component Analysis, YCbCr color space, Face recognition, Surveillance applications
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: FACULTY > Faculty of Engineering
Depositing User: Unnamed user with email storage.bpmlib@ums.edu.my
Date Deposited: 29 Nov 2016 03:11
Last Modified: 23 Oct 2017 07:48
URI: http://eprints.ums.edu.my/id/eprint/15008

Actions (login required)

View Item View Item