Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/29653
Title: iJADE authenticator - An intelligent multiagent based facial authentication system
Authors: Lee, RST
Keywords: Active contour model
iJADE model
Intelligent agents
Invariant face recognition
Neural networks
Issue Date: 2002
Publisher: World Scientific
Source: International journal of pattern recognition and artificial intelligence, 2002, v. 16, no. 4, p. 481-500 How to cite?
Journal: International journal of pattern recognition and artificial intelligence 
Abstract: In modern consumer e-shopping environments, customer authentication is a critical process for confirming the identify of the customer. Traditional authentication techniques that rely on the customers to proactively identify themselves (using various schemes) can effect the user-friendliness of the e-shopping experience, and therefore reduce the customers' preference for such facilities. In this paper, we propose an innovative intelligent multiagent-based environmental, called iJADE (intelligent Java Agent Development Environment) to provide an intelligent agent-based platform in the e-commerce environment. Contemporary agent development platforms are focused on the autonomy and mobility of the agents, whereas iJADE provides an intelligent layer (known as the "conscious layer") to implement various AI (artificial intelligence) functionalities in order to produce "smart" agents. From an implementation perspective, we introduce an innovative e-shopping authentication scheme called the "iJADE Authenticator", which is an invariant face recognition system that uses intelligent mobile agents. This system can provide fully automatic, mobile and reliable user authentication. More importantly, the authentication process can be carried out without the users necessarily being aware of it. Experimental results are presented for a database of 1 020 tested face images obtained under conditions of widely varying facial expressions, viewing perspectives and image sizes. An overall average correct recognition rate of over 90% is attained.
URI: http://hdl.handle.net/10397/29653
ISSN: 0218-0014
EISSN: 1793-6381
DOI: 10.1142/S0218001402001794
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Last Week
0
Last month
0
Citations as of Sep 8, 2017

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
0
Citations as of Sep 22, 2017

Page view(s)

31
Last Week
1
Last month
Checked on Sep 18, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.