Advanced face recognition and verification in mobile platforms
| DOI | https://doi.org/10.1108/JSIT-11-2013-0060 |
| Published date | 06 May 2014 |
| Pages | 126-137 |
| Date | 06 May 2014 |
| Author | Yong-Hwan Lee,Hyochang Ahn,Han-Jin Cho,June-Hwan Lee |
| Subject Matter | Information & knowledge management,Information systems |
Advanced face recognition and
verification in mobile platforms
Yong-Hwan Lee and Hyochang Ahn
Department of Applied Computer Engineering,
Dankook University, Yong-in si, Korea, and
Han-Jin Cho and June-Hwan Lee
Department of Smart Mobile, Far East University, Chungbuk, Korea
Abstract
Purpose – This paper holds a big advantage to enable to recognize faces, regardless of time and
place. Also this provides an independent performance of smart phone, because of its process by a
computer of third party not by that of the mobile device. In addition, it is desirable to minimize the
expensive operations in mobile device with constraint computational power (i.e. battery consumption).
Thus, the authors exclude the process of transmission failed from the input device. The paper aims to
discuss these issues.
Design/methodology/approach – In this paper, the authors have proposed a new face detection
and verification algorithm, based on skin color detection to enable extracting the face region from color
images of the mobile phone. And then extracted the facial feature as eigenface, verified whether or not
the identity of users is right, applied support vector machine to the region of detected face.
Findings – The experimental results for two datasets show that the proposed method achieves
slightly higher efficiencies at the detection and verification of user identity, compared with other
method, where varying lighting conditions with complex backgrounds, according to be fast and
accurate than any other previous methods.
Originality/value – The proposed algorithm enables to implement fast and accurate search using
triangle-square transformation for detection of human faces in a digital still color images, obtained by
the mobile device camera under unconstraint environments, using advanced skin color model and
characteristic points in a detected face.
Keywords Face detection,Face recognition and verification,Triangle-square transformation
Paper type Research paper
1. Introduction
Digital content usingon mobile device has recently increased.Since the requirements for
securityand convenience of a user are increased,many researches forface recognition and
verificationhave become more attractive than before.In case of recognizing a human face
on mobile device, facedetection should be acknowledged in consideration of a varietyof
illumination variations and location of mobile camera(Masip and Vitria, 2004). Over the
past few years,using internet services has increasedcontinuously, and there has beenan
important advanced in mobile device. With the technologies related to mobile device,
a novel user friendlyinterfaces are necessary for using them,and one of the most popular
and reliable approaches is an identification of user (Hafeez-Baig and Gururajan, 2009).
A verificationof user’s identity can be very important in theapplication such as financial
services, surveillance application, and verification for access control (Maditinos et al.,
2013). Sincethe traditional methods suchas password, personal identificationnumber are
easy tobroken, a bio-metric identificationsystem can be good solution for userverification
(Masip and Vitria, 2004). Bio-metric technology is currently to become a real product
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/1328-7265.htm
Received 11 November 2013
Revised 11 November 2013
Accepted 14 January 2014
Journal of Systems and Information
Technology
Vol. 16 No. 2, 2014
pp. 126-137
qEmerald Group Publishing Limited
1328-7265
DOI 10.1108/JSIT-11-2013-0060
JSIT
16,2
126
To continue reading
Request your trial