TITLE 1: EXPERIMENTAL EVALUATION OF MATCHING-SCORE

NORMALIZATION TECHNIQUES ON DIFFERENT MULTIMODAL

BIOMETRIC SYSTEMS.
AUTHOR: Slobodan Ribaric and Ivan Fratric
YEAR: IEEE MELECON 2006, MAY 16-19, BENALMDENA (MLAGA),
SPAIN
DESCRIPTION:
The goal of this work is experimental evaluation of matching-score normalization
techniques for the following three multimodal biometric systems: a verification
system based on the fusion of face and palm print principal line features, an
identification system based on eigen fingers and finger-geometry, and an
identification system based on eigen palm and eigen finger features. The following
normalization techniques are tested: Bayes-based normalization and several
heuristic techniques (min-max, zscore, median-MAD, double-sigmoid, tanh, and
piecewise linear). The results of evaluation are represented by means of system
performance (expressed by ROC, EER and min TER) and F-statistics.

TITLE 2: MULTIMODAL BIOMETRIC SYSTEM USING RANK-LEVEL

FUSION APPROACH
AUTHOR: Md. Maruf Monwar, Student Member, IEEE, and Marina L. Gavrilova,
Member, IEEE
YEAR: IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS
PART B: CYBERNETICS, VOL. 39, NO. 4, AUGUST 2009

DESCRIPTION:
In many real-world applications, uni modal biometric systems often face
significant limitations due to sensitivity to noise, intra class variability, data quality,
non-universality, and other factors. Attempting to improve the performance of
individual matchers in such situations may not prove to be highly effective. Multi
biometric systems seek to alleviate some of these problems by providing multiple
pieces of evidence of the same identity. These systems help achieve an increase in
performance that may not be possible using a single-biometric indicator. This paper
presents an effective fusion scheme that combines information presented by
multiple domain experts based on the rank-level fusion integration method. The
developed multimodal biometric system possesses a number of unique qualities,
starting from utilizing principal component analysis and Fishers linear
discriminant methods for individual matchers (face, ear, and signature) identity
authentication and utilizing the novel rank-level fusion method in order to
consolidate the results obtained from different biometric matchers. The ranks of
individual matchers are combined using the highest rank, Borda count, and logistic
regression approaches. The results indicate that fusion of individual modalities can
improve the overall performance of the biometric system, even in the presence of
low quality data. Insights on multi biometric design using rank-level fusion and its
performance on a variety of biometric databases are discussed in the concluding
section.
TITLE 3: FEATURE FUSION METHOD BASED ON KCCA FOR EAR AND
PROFILE FACE BASED MULTIMODAL RECOGNITION.
AUTHOR: Xiaona Xu and Zhichun Mu

YEAR: 2007 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION

AND LOGISTICS.
DESCRIPTION:
In this paper, a novel feature fusion method based on kernel canonical correlation
analysis (KCCA) is presented and applied to ear and profile face based multimodal
biometrics for personal recognition. Ear recognition is proved to be a new and
promising authentication technique. The fusion of ear and face biometrics could
fully utilize their connection relationship of physiological location, and possess the
advantage of recognizing people without their cooperation. First, the profile-view
face images including ear part were used for recognition. Then the kernel trick was
introduced to canonical correlation analysis (CCA), and the feature fusion method
based on KCCA is established. With this method, a kind of nonlinear associated
feature of ear and face was proposed for classification and recognition. The result
of experiment shows that the method is efficient for feature fusion, and the
multimodal recognition based on ear and profile face performs better than ear or
profile face uni modal biometric recognition and enlarges the recognition range.
The work provides a new effective approach of nonintrusive biometric recognition.

TITLE 4: A SHAPE- AND TEXTURE-BASED ENHANCED FISHER

CLASSIFIER FOR FACE RECOGNITION
AUTHOR: Chengjun Liu, Member, IEEE, and Harry Wechsler, Fellow, IEEE
YEAR: IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 10, NO. 4,
APRIL 2001
DESCRIPTION:

This paper introduces a new face coding and recognition method, the enhanced
Fisher classifier (EFC), which employs the enhanced Fisher linear discriminant
model (EFM) on integrated shape and texture features. Shape encodes the feature
geometry of a face while texture provides a normalized shape-free image. The
dimensionalities of the shape and the texture spaces are first reduced using
principal

component

analysis,

constrained

by

the

EFM

for

enhanced

generalization. The corresponding reduced shape and texture features are then
combined through a normalization procedure to form the integrated features that
are processed by the EFM for face recognition. Experimental results, using 600
face images corresponding to 200 subjects of varying illumination and facial
expressions, show that 1) the integrated shape and texture features carry the most
discriminating information followed in order by textures, masked images, and
shape images and 2) the new coding and face recognition method, EFC, performs
the best among the Eigen faces method using 1 or 2 distance measure, and the
Mahalanobis distance classifiers using a common covariance matrix for all classes
or a pooled within-class covariance matrix. In particular, EFC achieves 98.5%
recognition accuracy using only 25 features.
TITLE 5: FEATURE EXTRACTION FOR VIBRATION SIGNAL OF
ASYNCHRONOUS MOTOR BASED ON QUATERNION K-L TRANSFORM.
AUTHOR: Tong Jia Jiaxing University.
YEAR: 2010 INTERNATIONAL CONFERENCE ON ELECTRICAL AND
CONTROL ENGINEERING
DESCRIPTION:
This paper proposed a new method of feature extraction for vibration signals of
asynchronous motors based on quaternion K-L transform. The vibration signals

were detected by the vibration detector with three channels X, Y, Z, that were
orthogonal axes. We constructed quaternion sequence based on signals of the three
channels, and then the quaternion sequences were transformed by quaternion K-L
method to extract features for asynchronous motors with faults. In order to verify
its effectiveness, this method was applied combined with SVM classifier, the
experimental results had proved its efficiency and feasibility, and dominated that it
could be well applicable for asynchronous motor fault diagnosis.

TITLE 6: A MULTI-CLASSIFIER APPROACH TO MUAP CLASSIFICATION

FOR DIAGNOSIS OF NEUROMUSCULAR DISORDERS
AUTHOR: Tahereh Kamali, Reza Boostani, and Hossein Parsaei
YEAR:

IEEE

TRANSACTIONS

ON

NEURAL

SYSTEMS

AND

REHABILITATION ENGINEERING, VOL. 22, NO. 1, JANUARY 2014

DESCRIPTION:
The shapes and sounds of isolated motor unit action potentials (MUAPs) in an
electromyographic (EMG) signal provide a significant source of information for
diagnosis, treatment and management of neuromuscular disorders. These
parameters can be analyzed qualitatively by an expert or quantitatively by using
pattern recognition techniques. Due to the advantages of quantitative EMG
method, developing robust automated MUAP classifiers have been explored and
several systems have been developed for this purpose by now, but the accuracy of
the existing methods is not high enough to be used in clinical environments. In this
paper, a novel classification strategy based on ensemble of support vector
machines (SVMs) classifiers in hybrid serial/parallel architecture is proposed to

determine the class label (myopathy, neuropathic, or normal) for a given MUAP.
The developed system employs both time domain and time-frequency domain
features of the MUAPs extracted from an EMG signal using an EMG signal
decomposition system. Different classification strategies including single classifier
and multiple classifiers with several subsets of features were investigated.
Experimental results using a set of real EMG signals showed robust performance
of multi-classifier methods proposed here. Of the methods studied, the multiclassifier that uses multiple features sets and a combination of both trainable and
non-trainable fusion techniques to aggregate base classifiers showed the best
performance with average accuracy of 97% which is significantly higher than the
average accuracy of single SVM-based classifier system (i.e., 88%).

TITLE 7: FACE FEATURE WEIGHTED FUSION BASED ON FUZZY

MEMBERSHIP DEGREE FOR VIDEO FACE RECOGNITION
AUTHOR: Jae Young Choi, Member, IEEE, Konstantinos N. Plataniotis, Fellow,
IEEE, and Yong Man Ro, Senior Member, IEEE.
YEAR: IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS
PART B: CYBERNETICS, VOL. 42, NO. 4, AUGUST 2012
DESCRIPTION:
This paper proposes a new video face recognition (FR) method that is designed for
significantly improving FR via adaptive fusion of multiple face features (belonging
to the same subject) acquired from a face sequence of video frames. In this paper,
we derive an upper bound for recognition error arising from the proposed weighted
feature fusion to justify theoretically its effectiveness for recognition from videos.

In addition, in order to compute the optimal weights of face features to be fused,

we develop a novel weight determination solution based on fuzzy membership
function and quality measurement for face images. Using four public video
databases, the effectiveness of the proposed method has been successfully
evaluated under the conditions that are similar to those in real-world video FR
applications. Furthermore, our method is simple and straightforward to implement.
TITLE 8: FEATURE-LEVEL FUSION IN PERSONAL IDENTIFICATION
AUTHOR: Yongsheng Gao, Member, IEEE, Michael Maggs
YEAR: 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER
VISION AND PATTERN RECOGNITION (CVPR'05)
DESCRIPTION:
The existing studies of multi-modal and multi-view personal identification focused
on combining the outputs of multiple classifiers at the decision level. In this study,
we investigated the fusion at the feature level to combine multiple views and
modals in personal identification. A new similarity measure is proposed, which
integrates multiple 2-D view features representing a visual identity of a 3-D object
seen from different viewpoints and from different sensors. The robustness to nonrigid distortions is achieved by the proximity correspondence manner in the
similarity computation. The feasibility and capability of the proposed technique for
personal identification were evaluated on multiple view human faces and palm
prints. This research demonstrates that the feature-level fusion provides a new way
to combine multiple modals and views for personal identification.

TITLE

9:

FUSING

LOCAL

PATTERNS

OF

GABOR

AND

NON-

SUBSAMPLED CONTOURLET TRANSFORM FOR FACE RECOGNITION.

AUTHOR: Yao Deng, Zhenhua Guo, and Youbin Chen
YEAR: 2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN
RECOGNITION
DESCRIPTION:
In this paper, we propose a new face representation based on fusing local patterns
of Gabor and NSCT. Firstly, we decompose face images using Gabor and NSCT
respectively. Then all decomposition images are encoded by local texture
descriptors to combine. In order to extract efficient features for feature fusion, we
propose local Gabor difference features (LGDF) and local contourlet difference
features (LCDF) to represent the texture of decomposition images. Thirdly, after
fusing LGDF and LCDF, block-based Fishers linear discriminant (BFLD) is
utilized to further reduce the dimensionality and improve discriminative power of
the proposed method. Experiments on public databases demonstrate that the
proposed LGDF and LCDF are very effective and our approach outperforms many
state-of-the-art methods.
TITLE 10: ON THE USE OF DISCRIMINATIVE COHORT SCORE
NORMALIZATION FOR UNCONSTRAINED FACE RECOGNITION
AUTHOR: Massimo Tistarelli, Senior Member, IEEE, Yunlian Sun, and Norman
Poh, Member, IEEE
YEAR: IEEE TRANSACTIONS ON INFORMATION FORENSICS AND
SECURITY, VOL. 9, NO. 12, DECEMBER 2014

DESCRIPTION:
In this paper, a picture-specific cohort normalization approach, based on
polynomial regression, is proposed to enhance the robustness of face matching
under challenging conditions. A careful analysis is presented to better understand
the actual discriminative power of a given cohort set. In particular, it is shown that
the cohort polynomial regression alone conveys some discriminative information
on the matching face pair, which is just marginally worse than the raw matching
score. The influence of the cohort set size in the matching accuracy is also
investigated. Further, tests performed on the Face Recognition Grand Challenge
ver 2 database and the labeled faces in the wild database allowed to determine the
relation between the quality of the cohort samples and cohort normalization
performance. Experimental results obtained from the LFW data set demonstrate the
effectiveness of the proposed approach to improve the recognition accuracy in
unconstrained face acquisition scenarios.