 20082009
20102011
2012
2013
April
June
November
Issue : April 2009
DOI: BB042009001
Title: An Approach to Biometric Authentication Using
Hidden Markov Model
Authors: Malaya Dutta Borah, Ganesh Chandra Deka
Keywords: Hidden Markov Model (HMM), Fingerprints
Matching, Biometric Authentication, Parametric Random
Process, Texture Pattern, Welch Re-Estimation
Abstract:
One of the most challenging Biometric Authentication
is fingerprint identification. In 1893, the Home Ministry
office, UK accepted that no two individuals have the
same fingerprints, i.e never identical in every detail.
Due to this property fingerprints are widely used
by law enforcement applications. Fingerprint identification
system mostly consists of extraction, classification
and matching. In this paper we are going to propose
a theoretical model for fingerprint matching using
Hidden Markov Model (HMM). Our main focus is on extracting
reference information; detect sample vectors, pretreatment
including noise illumination and training process
of HMM engine. The underlying assumption of proposed
HMM is that the fingerprint texture pattern and orientation
can be well characterized as a parametric random process
and hence reduce the size of the search space of a
fingerprint database and accordingly increase the
speed of fingerprint matching
Full
PDF
Issue : April 2009
DOI: BB042009002
Title: Face Recognition Using Parallel Algorithm
Authors: N. Verma, S. C. Panigrahi and A. Mustafi
Keywords: Dilation, Face Recognition, Histogram, Local
Binary Patterns, Occurrence Map
Abstract:
In this paper we present a novel parallel implementation
of Local Binary Pattern based face recognition algorithm,
improving the recognition accuracy. An adaptive block
matching method is introduced in the context of the
proposed algorithm for parallel image processing.
The local binary pattern approach has evolved to represent
significant breakthrough in texture analysis, outperforming
earlier methods in many applications. Perhaps the
most important property of the LBP operator in real-world
applications is its tolerance against illumination
changes. Another equally important is its computational
simplicity, which makes it possible to analyze images
in challenging real-time settings. Our excellent results
suggest that that texture and the ideas behind the
LBP methodology could have a much wider role in image
analysis and computer vision than was thought before.
Extensive experiments clearly show the superiority
of the proposed scheme over all considered methods
(PCA, Bayesian Intra/extrapersonal Classifier and
Elastic Bunch Graph Matching) on FERET tests which
include testing the robustness of the method against
different facial expressions, lighting and aging of
the subjects. In addition to its efficiency, the simplicity
of the proposed method allows for very fast feature
extraction.
Full
PDF
Issue : April 2009
DOI: BB042009003
Title: Fingerprint Enhancement Based on Ridge Orientation
and Ridge Frequency
Authors: Mrs.S. Malathi, Mrs.S. Umamaheswari, Dr.C.
Meena
Keywords: Fingerprint Enhancement, Minutiae Extraction,
Ridge, Valley, Ridge Orientation, Ridge Frequency,
AFIS
Abstract:
The performance of any fingerprint recognizer
highly depends on the fingerprint image quality. Different
types of noises in the fingerprint images pose greater
difficulty for recognizers. Most Automatic Fingerprint
Identification Systems (AFIS) use some form of image
enhancement. Although several methods have been described
in the literature, there is still scope for improvement.
In order to ensure that the performance of an automatic
fingerprint identification system will be robust with
respect to the quality of input fingerprint images,
it is essential to incorporate a fingerprint enhancement
algorithm in the minutiae extraction module. This
paper presents a fingerprint enhancement algorithm,
which can adaptively improve the clarity of ridge
and valley structures of input fingerprint images
based on the estimated local ridge orientation and
frequency.
Full
PDF
Issue : April 2009
DOI: BB042009004
Title: Security Analysis of Multimodal Biometric Fuzzy
Vault
Authors: V.S. Meenakshi, Dr. G. Padmavathi
Keywords: Biometrics, Multi Biometrics, Fuzzy Vault,
Multi Biometric Fuzzy Vault, Biometric Template Security,
Min-Entropy, Crypto Biometric Systems
Abstract:
Crypto biometric systems are authentication
systems where the concept of biometric authentication
is blended with cryptography. Crypto-biometric systems
utilize the advantages of biometrics over traditional
password based authentication. This paper uses the
idea of fuzzy vault cryptographic constructs to protect
crucial data like secret encryption key. Fuzzy vault
is a proven emerging technology for providing biometric
template security. This work constructs two independent
fingerprint and iris vaults and a combined multimodal
biometric vault. The proposed multimodal biometric
fuzzy vault uses the features extracted from both
finger print and iris for ensuring high security of
the critical data and the biometric template. It is
comparatively difficult for an attacker to compromise
multi modal biometric fuzzy vault system than single
biometric fuzzy vault systems. This work measures
the security of the constructed fuzzy vault by means
of min-entropy.
Full
PDF
Issue : April 2009
DOI: BB042009005
Title: User Identification Using Keystroke Dynamics
Authors: Mrs. D. Shanmugapriya, Dr. G. Padmavathi
Keywords: Biometric, Entropy, False Acceptance Rate,
False Rejection Rate
Abstract:
Keyboard Entropy is a feature, which will try
to identify the authenticity of a user when the user
is working via a keyboard. The authentication process
is done by observing the change in the entropy of
the user. The objective of the paper is to design
and implement a biometric authentication scheme by
means of keyboard entropy to secure all applications,
which require password authentication. Username and
password pairs as authentication factors are as weak
as they are ubiquitous. Use of a single factor of
authentication is so weak that multi factor authentication
methods are required. The tolerance factor provides
a bit of leniency to check the authenticity of user.
It is introduced in the master data depending upon
how much deviation is caused by the user at different
times. This paper proposes two formulae for calculating
tolerance value which generates False Acceptance rate
(FAR) and False Rejection Rate (FRR).
Full
PDF
Issue : April 2009
DOI: BB042009006
Title: Gene Data Classification Using Hybrid Hierarchical
Multi-label Classifier
Authors: Santhi Thilagam and Rama Sri Sindhura
Keywords: Hierarchical Multi-Label Classification,
Gene Prediction, Predictive Clustering Trees
Abstract:
Gene function prediction is a multi-class classification
problem since genes typically play multiple roles
biologically. The predictions can then be given to
biologists for experimental validation. As such, we
face a more challenging classification problem than
typical binary classification that only needs to determine
whether a gene belongs to a particular functional
class or not. The solution to this problem has been
formulated using Predictive Clustering Trees and its
implementation exists. We attempt to improve the accuracy
of prediction of the results of the above implementation
using additional single classifiers. We define an
appropriate distance metric for hierarchical multi-classification
and present experiments evaluating this approach on
a number of data sets that are available for yeast.
Full
PDF
|
