Multimodal biometric system combining left and right palmprints

Publication Date31 August 2019
Date31 August 2019
AuthorChérif Taouche,Hacene Belhadef
SubjectLibrary & information science,Library & information services,Lending,Document delivery,Collection building & management,Stock revision,Consortia
Multimodal biometric system combining left
and right palmprints
Chérif Taouche
Laboratory, University of Oum El-Bouaghi, Oum El-Bouaghi, Algeria, and
Hacene Belhadef
NTIC Faculty, University of Constantine 2, Constantine, Algeria
Purpose Palmprint recognition is a very interesting and promising area of research. Much work has already been done in this area, but much more
needs to be done to make the systems more efcient. In this paper, a multimodal biometrics system based on fusion of left and right palmpri nts of a
person is proposed to overcome limitations of unimodal systems.
Design/methodology/approach Features are extracted using some proposed multi-block local descriptors in addition to MBLBP. Fusion of
extracted features is done at feature level by a simple concatenation of feature vectors. Then, feature selection is performe d on the resulting global
feature vector using evolutionary algorithms such as genetic algorithms and backtracking search algorithm for a comparison purpose. The benets
of such step selecting the relevant features are known in the literature, such as increasing the recognition accu racy and reducing the feature set size,
which results in runtime saving. In matching step, Chi-square similarity measure is used.
Findings The resulting feature vector length representing a person is compact and the runtime is reduced.
Originality/value Intensive experiments were done on the publicly available IITD database. Experimental results show a recognition accurac y of
99.17 which prove the effectiveness and robustness of the proposed multimodal biometrics system than other unimodal and multimodal biometrics
Keywords Multimodal biometrics, Feature selection, Local descriptor, Palmprint recognition, Feature fusion, Genetic algorithms, BSA
Paper type Research paper
1. Introduction
Palmprint recognition is a relatively new and novel biometric
authentication technology (Kong et al.,2009;Jain and Feng,
2009), and has received more and signicant attention from
researchers recently. As the palmprint possesses many types of
features like minutiae points,singular points, texture, principal
lines, wrinkles and patterns of ridges,it is more distinctive and
has the potential to achieve reliable and good performance in
biometric recognition (Zhang et al.,2012;Malik et al., 2015;
Yue et al., 2013).
Compared to other biometric modalities, the palmprint trait
satises the critical properties of biometric characteristics such
as universality, individuality, stability, and collectability. In
addition to having relatively stable and unique features even in
the monozygotic twins, the palmprintmodality is non-intrusive
and the collection of its data is very easy. In other words, it
requires less cooperation to collect data from individuals. By
using low-resolution images taken from the low-cost device, it
provides high efciency.Therefore, palmar recognition is a very
interesting and promising area of research. Much work has
already been done in thisarea, but much more needs to be done
to make the systems more efcient.
Although unimodal biometrics-based recognition systems
provide good performance, they still suffer from some problems
which cause them to be less secure and accurate, such as spoong,
noisy data, non-universality, partial occlusion, illumination
variation and pose variation (Mamta and Hanmandlu, 2015). To
overcome some of these inconveniences to increase recognition
accuracy and the level of security, multimodal biometric
authentication is a promising alternative. Multimodal biometrics
overcomes the above drawbacks by combining two or more traits
more than biometric trait makes it very difcultforanimposterto
spoof simultaneously multiple traits of a genuine user. Further,
multimodal identication resolves the non-universality problem,
since sufcient coverage of the population is ensured by multiple
traits (Hezil and Boukrouche, 2017).
Several researches were conducted on multimodal biometric
systems combining palmprint modality and other biometric
modalities such as ngerprints, face,ear, hand shape (Ghulam
Mohi-ud-Din et al., 2011;Raghavendra et al.,2011;Xu et al.,
2011,2013;Saini and Sinha, 2015;Farmanbar and Toygar,
2016;Hezil and Boukrouche,2017;Charet al.,2017;etc.).
Despite being complementary (even in real-life) and rich in
discriminatinginformation as noted above, very few works have
Emerald Insight at:
Information Discovery and Delivery
48/1 (2020) 213
© Emerald Publishing Limited [ISSN 2398-6247]
[DOI 10.1108/IDD-01-2019-0011]
Received 31 January 2019
Revised 23 April 2019
22 June 2019
Accepted 31 July 2019

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT