Face Recognition Using Combined Multiscale Anisotropic and Texture Features Based On Sparse Coding

IET Image Processing
Face recognition using combined multiscale anisotropic and

texture features based on sparse coding
Journal:
Manuscript ID:
IPR-2013-0876
Manuscript Type:
Research Paper
Date Submitted by the Author:

Complete List of Authors:
Keyword:
17-Feb-2014
Borgi, Mohamed Anouar; university of sfax, computer science
el arbi, maher
Labate, Demetrio; University of Houston, department of Mathematics
Ben Amar, Chokri
COMPUTER VISION, IMAGE PROCESSING, PATTERN RECOGNITION
IET Review Copy Only
Page 1 of 14
Face recognition using combined multiscale anisotropic

and texture features based on sparse coding
Mohamed Anouar Borgi1, Maher ElArbi1, Demetrio Labate2, Chokri Ben Amar1
1
Research Groups on Intelligent Machines, University of Sfax, Sfax 3038, Tunisia

2
Department of Mathematics, University of Houston, Houston, TX 77204, USA
{anoir.borgi@ieee.org ; dlabate@math.uh.edu ; maher.elarbi@gmail.com;
chokri.benamar@ieee.org}
Abstract. It has been demonstrated, in computer vision and pattern recognition,

that heterogeneous information fusion can produce higher accuracy than single
information. This is mainly because the use of multiple sources matchers for the
subject enables more information to be used for identification or verification. This
paper addresses this problem through a novel approach called Shearlet Network
(SN) which takes advantage of the sparse representation (SR) properties of
shearlets in face coding and recognition. Shearlets are derived from wavelets with
composite dilations, a method extending the traditional wavelet approach by
allowing for the construction of waveforms at various scales, locations and
especially at various orientations. The contributions of this paper are the
combination of the power of multi-scale representation with a unique ability to
capture geometric information and the use of a PCA-based approach to design a
fusion step by a refined model of belief function based on the Dempster-Shafer
rule. This last step is helpful to improve the processing of facial texture features.
We compared our new algorithm (SNPCA) against SN, and different state-of-thearts algorithms based FR. Our tests run on several face databases including
FRGC, CK+ database and others; show that this approach yields a very
competitive performance.
Keywords. Shearlet, Shearlets Network, Sparse Coding, Face Recognition
1
Introduction
Biometrics is an attractive area of pattern recognition and computer vision, in fact, the current
trend emphasizes biometrics which can collected static characters on the move, as the face, so
that there is significant interest in more sophisticated and robust methods to go beyond current
state-of-the-art FR methods. One of the most successful approaches to template-based face
representation and recognition is based on Principal Component Analysis (PCA). However,
PCA approximates texture only, while the geometrical information of the face is not properly
captured. In addition to PCA, many other linear projection methods have been considered in
face recognition applications. The LDA (Linear Discriminant Analysis) has been proposed [1]
as an alternative to PCA. This method provides discrimination among the classes, while the
PCA deals with the input data in their entirety without paying much attention for the
underlying structure. Moreover, to deal with the challenges in practical FR system, active
shape model and active appearance model [2] were developed for face alignment; LBP [3]
1
and its variants were used to deal with illumination changes ; and Eigenimages [4][5] and
probabilistic local approach [6] were proposed for FR with occlusion.
On the other hand, a new generation of multiscale methods has emerged in recent years which
go far beyond traditional wavelets and have been shown to have the potential to provide better
performing algorithms in a variety of biometric-based approach. The shearlet system is one
notable example of these new classes of multiscale systems, which has the ability to capture
anisotropic information very efficiently, outperforming traditional wavelets. One particularly
appealing feature of shearlets is that they combine a multiscale framework which is
particularly effective to capture the geometry of a face, together with a simple mathematical
construction which can be associated to a multiresolution analysis and enables fast numerical
processing.
We recall that some recent work using shearlets for FR has recently appeared [7] [40]. In this
work, we present a new method for FR, called shearlet network (SN), which is refinement of
the classical wavelet network (WN). In this approach, faces will be approximated by a linear
combination of weighted sum of shearlets and the weights will be used in the on-line
recognition stage to calculate the similarity score between Gallery and probe face. We use
PCA-based approach for a fusion step with SN to provide more depth to the facial texture
appearance of the face; this fusion is achieved via a model of belief function which will be
explained below.
The rest of this paper is organized as follows. Sec. 2 describe the related work on face
recognition based sparsity and information fusion based methods, In Sec. 3, we briefly
describe some background on shearlets. Sec. 4 presents the proposed face recognition method.
In Sec. 5, the experimental results of the proposed algorithm are demonstrated and compared
with other algorithms. Finally, Sec. 6 concludes this paper.
Related Work
Recently, FR via sparse representation based classification (SRC) [8] has received more
attention as a powerful tool for statistical modelling, sparse representation (or sparse coding)
and has been successfully applied to face processing applications. SRC casts the recognition
problem as one of classifying among multiple linear regressions and uses sparse
representations computed via l1 minimization for efficient feature extraction suppose then the
testing face image is represented as a sparse weighted combination of the training samples
and the classification is performed by comparing which class yields the least representation
error.
Besides SRC, another powerful method recently proposed is the Regularized Robust Coding
(RRC) approach [9] [39] which could robustly regress a given signal with regularized
regression coefficients. By assuming that the coding residual and the coding coefficient are
respectively independent and identically distributed, the RRC seeks for a maximum a
posterior solution of the coding problem. An iteratively reweighted regularized robust coding
algorithm was proposed to solve the RRC model efficiently.
Although SRC performs well when the set of training images is sufficiently large, it is still
inadequate for many real world applications where only a single sample per subject is
available.
As a part of this work, a step a belief fusion, we will present next a simple review on
information fusion based methods. In fact, Nowadays, Information fusion has been employed
2
Page 2 of 14
Page 3 of 14
as an efficient tool for the alliance of data acquired from different sources. In particular, face
recognition was a niche where information fusion was applied broadly. Fusion techniques are
frequently used when both shape and texture modalities are available. The standard approach
is to design separate classifiers for each individual modality and to combine them at the score,
rank, or decision level. A typical example of this approach is given in the work of K. I. Chang
et al [10] where PCA-based matchers was used for shape (depth image) and texture modalities
and fused their match scores by a weighted sum rule.
G. Pan et al [11] present a face recognition system that combines profile and surface
matchers. The three profile experts use one vertical and two horizontal profile measurements.
The surface expert makes use of a weighted ICP-based surface matcher. The similarity scores
from these four matchers are combined by the sum rule.
Gkberk et al. [12] have briefly discussed shape-only features such as point-cloud-, surfacenormal-, depth-image-, and profile-based shape information. In this first round of fusion
experiments, they have observed that some fusion schemes outperform the best individual
classifier. They experimented with various combination methods such as fixed rules at score
level (sum/product), rank-based combination rule (Borda count), and abstract-level voting
method (plurality voting). In addition, they have proposed a two-level serial-fusion scheme
where the first level functions as a prescreener, whereas the second level uses linear
discriminant analysis (LDA) to better separate the gallery images.
Another type of shape-based expert fusion is proposed in [13]. This approach is essentially a
multiregion approach where different facial-region pairs from the gallery and probe images
are matched, and the matching scores are combined with the product rule. The local experts
compute the surface similarities of three overlapping regions around the nose by using the
ICP algorithm, and their registration errors by these three surface matches are then combined.
A feature-level fusion scheme is presented in [14] where global shape features are
concatenated with the local features. The dimensionality of the concatenated vector is reduced
by the PCA method.
Fusion techniques are frequently used when both shape and texture modalities are available.
The standard approach is to design separate classifiers for each individual modality and to
combine them at the score, rank, or decision level. A typical example of this approach is given
in [15] where PCA-based matchers was used for shape (depth image) and texture modalities
and fused their match scores by a weighted sum rule. Another approach is proposed by C. Ben
Abdelkader et al [16] who use a local-feature-analysis (LFA) technique instead of the
classical PCA to extract features from both shape and texture modalities. This classifier
combines texture and shape information with the sum rule. Another interesting variant is the
data-level fusion. The depth-image pixels are concatenated to the texture-image pixels to form
a single vector. LDA is then applied to the concatenated feature vectors to extract features.
Mian et al. [42] propose the use of local textural and shape features together in order to cope
with the variations caused by expressions, illumination, pose, occlusions, and makeup. The
textural features are based on scale-invariant feature transform. Tensors constructed in locally
defined coordinate bases are used as 3-D descriptors. The two schemes are fused at score
level with confidence-weighted sum rule.
3
Page 4 of 14
A prominent example of fusion of shape- and texture-based matching schemes is presented by

Y. Wang et al [18] where 2-D Gabor wavelet features is selected as local descriptors for the
texture modality, and point signatures are used as local 3-D shape descriptors. These featurebased representations are matched separately using the structural Hausdorff distance, and then
their similarity scores are fused at the score level by using a weighted sum rule.
A different algorithm that uses feature fusion via hierarchical graph matching (HGM) is
presented by M. Husken et al [19]. HGM has the role of an elastic graph that stores local
features in its nodes and structural information in its edges. HGM is fitted to both the textureimage and shape features since the shape image is registered to the texture image. The scores
produced from texture and shape HGMs are then fused by a weighted sum rule.
Our motivation, in this work, that Information is by-passed by the uncertainty, the
indistinctness and the ambiguity. Evidence theory is a flexible frame to model the ignorance
and the arbitrary and offers a natural context to remedy from all those information weakness.
One of this theory keys, belief functions remains the most widely known method, which
combines different pieces of evidences into a single value that approximates the probability of
an event [20].
In this paper, we use two different sources of information completely independent, shearlet
network algorithm and PCA based algorithm, two different confusion matrixes are obtained
then two mass belief functions vectors are used for the fusion which will be made via
Dempster-Shafer rule combination.
3
Background on Shearlets
The shearlet representation has emerged in recent years as one of the most effective
frameworks for the analysis and processing of multidimensional data [21]. The shearlet
approach is derived from the theory of wavelets with composite dilatation, a method
providing a general framework for the construction of waveforms defined not only at various
scales and locations, as traditional wavelets, but also at various orientations and with different
scaling factors in each coordinate. As shown in several publications [22][23] shearlets are
particularly effective in a number of image processing application, such as denoising and
feature extraction, where it is important to capture the geometric information efficiently. As a
generalization of the traditional wavelet approach, the continuous shearlet transform [24], is
defined as the mapping:
SH ( a , s , t ) = f , a , s ,t , a > 0, s , t
where, ast ( x ) = det M as
1
2
(1)
( M as ( x t )), and Mas = a s .
The shearlet transform is a function of three variables: the scale a, the shear s and the
translation t. By choosing the generator function appropriately, one can construct a collection
of functions ast ( x ) , called shearlets, which are well-localized waveforms at various scales,
orientations and locations. One of the main properties of the Continuous Shearlet Transform
is its ability to describe very precisely the geometry of the singularities of a 2-dimensional
function f [41].
4
Page 5 of 14
Fig. 2. Directional filters of shearlet.

By sampling the Continuous Shearlet Transform SH ( a, s, t ) on an appropriate discrete set we
1 1
obtain a discrete transform. Specifically, M as is discretized as M jl = Bl A j , where B =
,
0 1
4 0
A=
are the shear matrix and the anisotropic dilation matrix, respectively. Hence, the
0 2
discrete shearlets are the functions of the form:
3j
j
j,l,k (x) = 2 2 (Bl A x k) , j 0, 2 l 2 1, k
(2)
Figure 1 illustrates the two-level shearlet decomposition of a face image from Yale database,
where the first-level and and the second-level decomposition generates 8 subbands
corresponding to the different directional bands.
Fig. 2. The top image is the original Face image. The image below the top image contains the
approximation shearlet coefficients. Images of the detail shearlet coefficients are shown
below.
4
The Proposed Approach
The proposed approach is organized as follows. The Gallery faces are approximated by a
shearlet network (SN) to produce a compact biometric signature. It is this signature,
constituted by shearlets and their weights, which will be used to match a Probe with all faces
in the Gallery. In the recognition stage, the Test (Probe) face is projected on the shearlet
network (SN) of the Gallery face and new weights specific to this face are produced. The
family of shearlets remains then unchanged (that of the Gallery face). Finally, a similarity
score is produced by comparing the weights of the Gallery face with the weights of the test
5
Page 6 of 14
face. In another section of the pipeline, PCA is used for FR [17] in order to generate the
eigenfaces from Gallery dataset which will be operated for the projection step of Probe
dataset. Those two matchers, SN and PCA, will generate two confusion matrixes which are
used to fill two belief mass matrixes with belief functions. Finally, we combined those
matrixes using a conjunction fusion rule. The pipeline of all these stages is illustrated in
Figure 2.
Fig. 3. Framework of 2D face recognition by Shearlet Networks and PCA.

4.1
Learning by Shearlet Network (SN)
A SN is a combination of the RBF neural network and the shearlet decomposition. The SN
algorithm approximates a 2D face image f using a linear combination of shearlet functions in
the network that are multiplied by corresponding weights according to:
~
f = w j ,l , k j ,l , k
(3)
j ,l , k
Fig. 4. Shearlet Network architecture.

6
Page 7 of 14
where f is the face image, f is the face image approximation, w j ,l ,k are the weights and
w j ,l , k are
the shearlet functions. An important part in the design of this method is the weights
optimization. For an image f , an energy (error) function is specified which is minimized

through a learning process with respect to the desired SN parameters.
E = m in
i
f i w j , l , k
j ,l , k
(4)
j ,l ,k
The mother shearlet used in our work to construct the family { j ,l ,k } is the second derivate of
the beta function. Details regarding beta function can be found in the work of C. Ben Amar et
al [25].
The algorithm used for the FR by SN is based the frames theory for the weights calculations
[26]. By sampling the continuous shearlet transform SH ( a , s, t ) on an appropriate
discretization lattice for the scaling, shear, and translation parameters ( a, s, t ) , one obtains a
discrete transform which is associated to a Parseval (tight) frame for L2 ( 2 ) . Indeed, we
obtain a discrete system of shearlets { j ,l ,k } , for j , l , k
which, for an appropriate
generator, satisfies the reproducing formula:

f =
j , l , k 2
f , j ,l , k j ,l , k
(5)
In the optimization stage, a shearlet coefficient from the library is processed through the
hidden layer of the network and used to update the weights. In order to know if a shearlet (n)
will be an activation function of a new "neuron", we must verify if it is a linear combination
of the other (n-1) shearlets of the network. The calculation of the weights connection in every
stage is obtained by projecting the image to be analysed on a family of shearlets. Hence, for a
given family of shearlets it is not possible to calculate the weights by direct projection of the
function f . At every stage of the optimization process we need to know the dual family of the
shearlets forming our shearlet network. The dual shearlet family is calculated by the formula:
~i
j ,l , k
= ( i , m ) j ,l , k with i,m = j ,l ,k , j,l ,k

m =1
(6)
We can summarize those steps on the following algorithm:

Algorithm 1: Learning SN
Input: image f , the number of shearlets
Output: reconstructed image f rec
1. Select a shearlet { j ,l ,k } as activation function of the shearlet network:

a. Choose the mother shearlet.
b. Build a library formed by the shearlets which form a shearlet frame.
c. Set as a stop learning condition (the number of shearlets) and iterate the following
steps:
7
Page 8 of 14
~i
2. If not a tight: Calculate the dual basis
new selected shearlet according (6), Else
j ,l , k
formed by the shearlets of the network and the

~ i
j ,l ,k =
j ,l , k
.
~i
3. Calculate the weights by direct projection of the image on the dual shearlet
w =< f ,
i
j ,l , k
>.
4. Calculate the output of the network f rec .

5. If the number of shearlets is reached the learning stops, otherwise another shearlet is
selected and we return to step 2.
We computed the Euclidian distance d ( wi , wt ) for each pair of faces (gallery and test) using
Shearlet Network weights wi , wt . wt is generated by projecting the test face on the frame of
shearlets produced by the gallery faces and a confusion matrix is then obtained.
4.2
PCA based texture extraction
Principal component analysis is a classical feature extraction and data representation

technique widely used in the areas of pattern recognition and computer vision. PCA suggest
that any face image could be reconstructed approximately as a weighted sum of a small
collection of images that define a facial basis (eigenimages), and a mean image of the face
[27].
Within this context, it has been presented the well-known Eigenfaces method for face
recognition in 1991. Since then, PCA has been widely investigated and has become one of the
most successful approaches in face recognition. In the work of P.S. Penev et al [28], the
authors discussed the problem of the dimensionality reduction of the "face space" when
eigenfaces are used for representation. However, PCA approximates texture only, while the
geometrical information of the face is not properly captured.
In our approach PCA is used for FR in order to generate the eigenfaces from Gallery dataset
which will be operated for the projection step of test dataset. We computed the distance
d ( Ef i , Ef t ) for each pair of faces (gallery and test, Ef is eigenface) and a second confusion
matrix is then constructed.
4.3
Fusion by Belief Function
A step to normalize similarity matrices is essential, before combination, to generate

meaningful distances from the two matchers: SN and PCA. In this paper, we use the Min-Max
normalization, which has the following formula:
d '=
d d MIN
(7)
d MAX d MIN
Where d MAX , d MIN , d , d ' denote respectively the maximum, the minimum, the original and
the normalized distances. In the second step, we use a Bayesian assignment [29 to compute
the belief mass functions values from the confusion matrix. Finally, a conjunctive
combination rule [30] defined by the following equation is used to fuse confusion matrices.
mSN PCA ( A) = mSN mPCA ( A) =
mSN ( B ) mPCA ( C ) , A
BC = A
8
(8)
Page 9 of 14
Assuming that mSN PCA () 1 :

if A=
0
mSN PCA ( A) = mSN PCA ( A)

otherwise
1 m
SN PCA ( )
(9)
With mSN and mPCA the two Belief mass functions associated to SN and PCA.
Experimental Results
We run our experiments using standard benchmark face databases to evaluate the
performance of the proposed approach. We used the Extended Cohn-Kanade (CK+) [31], FEI
[32], Extended YALE B [33] and FRGC v1 [34] face databases. All the images are copped
except the Extended Cohn-Kanade (CK+) database and resized to 2732.
In this paper, we chose to select randomly the face image both for Gallery and Probe dataset.
A description of the databases used in Table 1 and examples of subjects (Gallery and Probe)
in Figure 3.
Database
Database
Size
Subject
number
CK+
FEI
Yale B
593
2800
16128
123
200
38
FRGC
v1
4003
152
Table 1. Description of the different databases used.
Fig.5. A subject from Gallery and Probe with different databases.

(a) FRGC. (b) Yale B. (c) FEI. (d) Extended CK+.
Most work in the literature uses multiple training samples per subject. However, an emerging
tendency in FR is to use Single Training Sample per Subject (STSS) [35] [36] [37] which is
a more challenging problem. By applying such strategy to the images from the databases
indicated above, we obtain a similarity matrix of 38x38 comparisons for Extended YALE B,
123 x123 comparisons for Extended Cohn Kanade (CK+), 152 x152 comparisons for FRGC
v1, and 200 x200 comparisons for FEI, which significantly reduce the computational
complexity of the algorithm compared to traditional multiple training samples per subject.
Hence, the similarity values located in the diagonal of the matrix are intra-class (the same
person) and the others are inter-class (different persons) or imposter access. In this paper, we
9
Page 10 of 14
considered the problems of face coding, recognition and authentication. Results are provided
in next subsections.
5.1
Face Coding (FC) Evaluation:
We use some standard quality measurement tool, such as the Peak Signal to Noise Ratio
(PSNR) and the Normalized Cross Correlation (NCC). We compared the two approaches, e.g,
SN vs. WN, and to the standard shearlet representation. We test with 3 face images, taken
randomly, for the same person from YALE database. The SN (table 2) is found to outperform
the two other methods that we considered.
Method
Shearlet
WN
SN
Test1
Test2
PSNR
NCC
PSNR
NCC
27.1227 0.9913 26.1698 0.9853
36.9600 0.9967 33.4986 0.9942
37.7788 0.9973 36.2613 0.9970
Test3
PSNR
NCC
26.1582 0.9861
32.5192 0.9931
35.8314 0.9962
Table 2. PSNR and NCC of different methods. (higher is better)

In order to have the same experimental protocol and conditions for FC we chose a shearlets
number (SN) equal to wavelets number (WN) equal to filters number of shearlet-based
approach. We can also plot the reconstruction error versus the number of employed wavelets
(WN) and shearlets of (SN).
5.2
Face Recognition using STSS
The following experiments illustrate our results regarding authentication and recognition
tasks. In these experiments, similarity matrices and mass belief functions matrices are
produced, rank-one recognition rates (Rank-1) are computed and evaluation Receiver
Operator Characteristic (ROC) curves are plotted. Table 3 summarize the rank-one
recognition rates (Rank-1). SNPCA, the proposed approach, presents a Rank-1 which
outperforms SN, BHDT [38], PCA approaches with whole the face databases.
Method
PCA
BHDT
[41]
SN
SNPCA
Extended
CK+
80.49
91.87
FEI
Yale B
FRGC v1
59.00
62.50
51.50
84.81
12.50
26.97
95.94
96.75
79.50
85.50
97.37
97.37
34.87
43.50
Table 3. Rank-1 with different subsets database (%).
10
Page 11 of 14
some experiments are illustrated in Figure 5, one image for each one of the 5 face database
considered. Each figure shows an ROC curve, where the x-axis represents the False Accept
rate. The figures show that SNPCA provides consistently the best performance.
100
100
95
90
90
85
85
Probability of Rejection
95
80
75
70
65
PCA
WN
SN
SNPCA
60
55
50
0
10
75
70
65
PCA
WN
SN
SNPCA
60
55
50
0
10
10
False Accept Rate (%)
80
10
10
(a)
10
(b)
100
100
90
80
90
80
70
60
40
0
10
10
60
50
40
30
PCA
SN
SNPCA
WN
PCA
50
70
20
WN
SN
10
10
0
0
10
(c)
SNPCA
1
10
10
(d)
Fig.6. ROC curves with (a) Extended Cohn-Kanade (CK+) database, (b) FEI database,
(c) Extended Yale B database, (d) FRGC v1 database.
From Table 2, we notice that SN gives better results in terms of

PSNR and NC as compared to WN and shearlet coding. This is due to the superior ability of
SN to capture the geometry of the data. Also for FR applications
the SN performs better than PCA and BHDT as shown by Table 3 and Figure 5.
Moreover, the combination of PCA and SN (SNPCA) using belief functions
improves considerably the recognition rates. This shows that features (texture
11
feature for PCA and anisotropic feature for

on different approaches can be effectively combined.
Page 12 of 14
SN)
from
matchers
based
Conclusion
This paper presents a novel sparse coding (SC) model for robust face recognition (FR) called
Shearlet Network (SN). This method was performed via fusion step by PCA-based approach
to provide more depth to facial texture feature, using a refined model of belief function based
on the Dempster-Shafer rule. One important advantage of SNPCA is its robustness to various
types of challenging scenarios of FR (pose, expression and illumination). This paper focussed
on the challenging problem of a single training sample per subject. In order to illustrate and
validate our approach we used the Extended Cohn-Kanade (CK+), FEI, Extended YALE B
and FRGC v1 face databases. Our results show that our approach is very competitive in terms
of recognition rate with respect to other standard and state-of-the-art methods.
References
[1] Lu, J., Plataniotis Kostantinos, N., Venetsanopoulos Anastasios, Face recognition using
LDA-based algorithms. IEEE Trans. Neural Networks 14 (1), 195200. 2003.
[2] Lanitis , A., Taylor , C.J., Cootes, T.F.: Automatic Interpretation and Coding of Face
Images Using Flexible Models, IEEE Trans. Pattern Analysis and Machine Intelligence,
1997, 19, (7), pp. 743-756
[3] Ahonen, T., A., Hadid, Pietikainen, M.: Face description with local binary patterns:
Application to face recognition, IEEE Trans. Pattern Analysis and Machine Intelligence,
2006, 28, (12), pp.20372041
[4] A. Leonardis and H. Bischof, Robust recognition using eigenimages, Computer Vision
and Image Understanding, vol. 78, no. 1, pp. 99-118, 2000.
[5] S. Chen, T. Shan, and B.C. Lovell, Robust face recognition in rotated eigenspaces, Proc.
Intl Conf. Image and Vision Computing New Zealand, 2007.
[6] A.M. Martinez, Recognizing Imprecisely localized, partially occluded, and expression
variant faces from a single sample per class, IEEE Trans. Pattern Analysis and Machine
Intelligence, vol. 24, no. 6, pp. 748-763, 2002.
[7] W. R. Schwartz and R. D. da Silva and L. S. Davis and H. Pedrini. "A Novel Feature
Descriptor Based on the Shearlet Transform". IEEE International Conference on Image
Processing, pp. 1033-1036, 2011.
[8] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma. Robust face recognition via
sparse representation. IEEE PAMI, 31(2):210227, 2009.
[9] M. Yang, L. Zhang, J. Yang and D. Zhang, Robust sparse coding for face recognition,
Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2011.
[10] K. I. Chang, K.W. Bowyer, and P. J. Flynn, An evaluation of multimodal 2D + 3D face
biometrics, IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 4, pp. 619624, Apr. 2005.
[11] G. Pan and Z. Wu, 3D face recognition from range data, Int. J. Image Graph., vol. 5,
no. 3, pp. 573593, 2005.
12
Page 13 of 14
[12] B. Gkberk, A. A. Salah, and L. Akarun, Rank-based decision fusion for 3D shapebased face recognition, in Proc. Audio-Video-Based Biometric Person Authentication T.
Kanade, A. Jain, and N. K. Ratha, Eds., 2005, vol. 3456, pp. 10191029. 2005.
[13] K. Chang, K. Bowyer, and P. Flynn, Adaptive rigid multi-region selection for handling
expression variation in 3D face recognition, in Proc. IEEE Workshop Face Recog. Grand
Challenge Experiments, pp. 157, 2005.
[14] C. Xu, Y. Wang, T. Tan, and L. Quan, Automatic 3D face recognition combining global
geometric features with local shape variation information, in Proc. Int. Conf. Autom. Face
Gesture Recog., pp. 308313,2004.
[15] K. I. Chang, K.W. Bowyer, and P. J. Flynn, An evaluation of multimodal 2D + 3D face
biometrics, IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 4, pp. 619624, Apr. 2005.
[16] C. Ben Abdelkader and P. A. Griffin, Comparing and combining depth and texture cues
for face recognition, Image Vis. Comput., vol. 23, no. 3, pp. 339352, Mar. 2005.
[17] A. Mian, M. Bennamoun, and R. Owens, 2D and 3D Multimodal Hybrid Face
Recognition, Proc. ECCV, pp. 344355, 2006.
[18] Y. Wang and C.-S. Chua, Robust face recognition from 2D and 3D images using
structural Hausdorff distance, Image Vis. Comput., vol. 24, no. 2, pp. 176185, Feb. 2006.
[19] M. Husken,M. Brauckmann, S. Gehlen, and C. von der Malsburg, Strategies and
benefits of fusion of 2D and 3D face recognition, in Proc. IEEE Workshop Face Recog.
Grand Challenge Experiments, 2005, p. 174, 2005.
[20] Yager, R.R., Liu, L.: Classic works of the Dempster-Shafer theory of belief functions. In:
Studies in fuzziness and soft computing, vol. 219. Springer, Heidelberg, 2008.
[21] P. S. Negi and D. Labate, "3D discrete shearlet transform and video processing", IEEE
Trans. Image Process. 21(6) pp. 2944-2954, 2012.
[22] G. R. Easley, and D. Labate, "Critically sampled wavelets with composite dilations",
IEEE Trans. Image Process., 21 (2) pp. 550-561, 2012.
[23] S. Yi, D. Labate, G. R. Easley, and H. Krim, "A Shearlet approach to Edge Analysis and
Detection", IEEE Trans. Image Process, 18 (5) pp. 929941, 2009.
[24] G. Kutyniok and D. Labate, "Resolution of the wavefront set using continuous shearlets",
Trans. Amer. Math. Soc. 361 pp. 2719-2754, 2009.
[25] C. Ben Amar, M. Zaied and M.A. Alimi, "Beta Wavelets. Synthesis and application to
lossy image compression", Journal of Advances in Engineering Software, Elsevier edition, 36
(7) pp. 459-474, July 2005.
[26] M. Zaied, O. Jemai and C. Ben Amar, "Training of the Beta wavelet networks by the
frames theory: Application to face recognition", the international Workshops on Image
Processing Theory, Tools and Applications, Tunisia, November 2008.
[27] M. Kirby and L. Sirovich, Application of the KL Procedure for the Characterization of
Human Faces, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp.
103-108, Jan. 1990.
[28] P.S. Penev and L. Sirovich, The Global Dimensionality of Face Space,Proc. Fourth
IEEE Intl Conf. Automatic Face and Gesture Recognition, pp. 264-270, 2000.
13
[29] D. Mercier, G. Cron, T. Denoeux and M. Masson. "Fusion of multi-level decision

systems using the Transferable Belief Model", Proc. FUSION, Philadelphia, PA, USA, July
2005.
[30] T. Denoeux. "Conjunctive and Disjunctive Combination of Belief Functions Induced by
Non Distinct Bodies of Evidence". Artificial Intelligence, Vol. 172, pages 234264, 2008.
[31] Lucey, P., Cohn, J. F., Kanade, T., Saragih, J., Ambadar, Z., & Matthews, I. "The
Extended Cohn-Kande Dataset (CK+): A complete facial expression dataset for action unit
and emotion-specified expression", Proc. CVPR,Workshop H CBA, 2010.
[32] C. E. Thomaz and G. A. Giraldi. "A new ranking method for Principal Components
Analysis and its application to face image analysis
[33]A. S. Georghiades and P. N. Belhumeur, "From Few to Many: Illumination Cone Models
for Face Recognition under Variable Lighting and Pose", IEEE Trans. on. PAMI, vol.23,
no.6, pp.643-660, June 2001
[34] P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, J. Marques,
J. Min, and W. Worek, "Overview of the face recognition grand challenge", Proc. CVPR05,
no. 1, pp. 947-954, June 2005
[35] Meng Yang, Lei Zhang, and David Zhang, "Efficient Misalignment Robust
Representation Representation for Real-Time Face Recognition Classification," Proc. ECCV
2012.
[36] P. Zhu, L. Zhang, Q. Hu, Simon and C.K. Shiu, "Multi-scale Patch based Collaborative
Representation for Face Recognition with Margin Distribution Optimization," Proc. ECCV
2012.
[37] Y. Su, S.G. Shan, X.L. Chen, and W. Gao, Adaptive Generic Learning for Face
Recognition from a Single Sample per Person, Proc. CVPR, 2010.
[38] H. Cevikalp, New clustering algorithms for the support vector machine based
hierarchical classification, Pattern Recognition Letters, 31(11), pp. 1285-1291, 2010.
[39] M. Yang, L. Zhang, J. Yang and D. Zhang, Regularized Robust Coding for Face
Recognition. IEEE Trans. on Image Processing, 2013.
[40] W. R. Schwartz and H. Guo and J. Choi and L. S. Davis. "Face Identification Using
Large Feature Sets". IEEE Transactions on Image Processing, vol. 21, n. 4, pp. 2245-2255,
2012.
[41] G. R. Easley, D. Labate and V. Patel, "Directional multiscale processing of images using
wavelets with composite dilations", to appear in J. Math. Imag. Vision, 2013.
[42] Blanz, V., Vetter, T., 2003. Face recognition based on fitting a 3D morphable model.
IEEE Trans. Pattern Anal. Machine Intell. 25 (9), 10631074, 2003.
14
Page 14 of 14

Face Recognition Using Combined Multiscale Anisotropic and Texture Features Based On Sparse Coding

Hochgeladen von

Dokumentinformationen

Originaltitel

Copyright

Verfügbare Formate

Dieses Dokument teilen

Dokument teilen oder einbetten

Freigabeoptionen

Stufen Sie dieses Dokument als nützlich ein?

Sind diese Inhalte unangemessen?

Copyright:

Verfügbare Formate

Face Recognition Using Combined Multiscale Anisotropic and Texture Features Based On Sparse Coding

Hochgeladen von

Copyright:

Verfügbare Formate

IET Image Processing