Sliding Window Based Fast Corner Matching Palmprint Authentication

Sliding Window Based Fast Corner Matching Palmprint Authentication

Jyoti Malik (National Institute of Technology Kurukshetra, India), G. Sainarayanan (Maples ESM Technologies Chennai, India) and Ratna Dahiya (National Institute of Technology Kurukshetra, India)
Copyright: © 2011 |Pages: 19
DOI: 10.4018/ijcvip.2011070102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Authentication time is the main and important part of the authentication system. Normally the response time should be fast but as the number of persons in the database increases, there is probability of more response time taken for authentication. The need of fast authentication system arises so that authentication time (matching time) is very less. This paper proposes a sliding window approach to make fast authentication system. The highlight of sliding window method is constant matching time, fast and can match translated images also. Several palmprint matching methods like match by correlation etc. are dependent upon the number of corners detected and so is the matching time. In sliding window method, matching time is constant as the numbers of matching operations are limited and the matching time is independent of the number of corners detected. The palmprint corner features extracted using two approaches Phase Congruency Corner Detector and Harris Corner Detector are binarized so that only useful information (features) is matched. The two approaches of Phase Congruency Corner Detector and Harris Corner Detector, when matched with hamming distance using sliding window can achieve recognition rate of 97.7% and 97.5% respectively.
Article Preview

2. Palmprint Authentication System

In this paper, the palmprint authentication system is divided in following two subsystems:

  • a)

    Pre- Authentication System

  • b)

    Authentication System

In Pre-authentication system (Figure 1), a database of Palmprint features and Reference threshold is prepared. These values will be used in training the system.

Figure 1.

Palmprint pre-authentication system

In Authentication system (Figure 2), the person is considered genuine or imposter based on the value of Reference threshold value stored in Pre-authentication system database.

Figure 2.

Palmprint authentication system

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing