2004 International Conference on Image Processing (ICIP)

A SVM-BASED METHOD FOR FACE RECOGNITION USING A WAVELET-

PCA REPRESENTATION OF FACES
Majid Safari, Mehrtash T. Harandi and Babak N. Araabi
Control and Intelligcnt Processing Centcr of Exccllcncc
Dcpaitment of E l d i i c a l and Computer Engineering, Univcrsitv of Tehran, Tehran, Iran
&
School of cognitive science (SCS)
lnstitutc for studies in theoretical physics and mathematics (IPM), Tehran, Iran
111 .wtfbri:&e. .slmrif..edfr , i i i h ( ? r ~ i i i [ i ~ ~U!.~ , cireK-
~ UL'. . < 7 1 ~ ~ 1 ( i h i ~ $nc.
l I l .ir-

ABSTRACT faccs and introduced the Eigcnlhce method Ibr l i c e

recognition [4]. PCA delivers a low dimensional
T1iI.s paper propose.^ a rzew nietliod oJ Jace rcprcscntation of an image and cxtincts a compact glohal
repmwrrtatim n,/iich is irsedfo~face ~ ~ ~ p i t iby o SVh
t i I. structure h-om it. On the other hand, IJM extracts
For.fnce rqneserltatiori we /raw irseci a iwo-step ndroii, discriminaton. ~caturcs so that the class- can be
Di.ccrute Wavelet Trarisfor7n (111V77
Jrrr t~vo-~iiirierisiorral differentiated in an optimum way. 'Thcsc two lincnr
is irscri io transfor711 the faces to a iiiore riiscririririoteci methods can he changed to some nonlincai- methods by
.space arid theii Priricipal Cornporieirt Aria/,wis (PCA) is means of Kernel functions (i.e. KPCA and KDA, [7]).
applied The proposed rr~ethorlproduced a .sigrirJcarzt Applying PCA on wavelet diagonal detail coefficients of
inrpiowrrieirt which incliicies a sirbstarifial reduction iri imagcs was examincd by Yucla [9]. After represcnting
ewer rate and in tirite ofprocessing cltririg the obtaining faces in a lower dimension space, a classifier such as
PCA or?honor?rtalbasis. nearest distance classifier, k-nearest neighborhood, neural
network or support vector machine (SVM) [3], [8])can be
1. INTRODUCTION applied to perform the recognition process. Recently,
interests on using SVM have been increased because of its
Several features (height, iris, fingqrint, voice, face) promising s p e d and accuracy.
have been uscd for human identification. Face recognition In this work S V M is used as a face classifier with
is a natura!, user friendly and non-contact way for human RBF and polynomial kernel function. We also utilized
identiBcation/authentication.Face recognizers are used in DWT as a preprocessing tool for face representation. The
the r e n t years for identity authentication, access control, new proposed method decreases the error rate by more
surveillance, human-computer interface and marl than 2.5% comparing to the PCA. The proposed method
environments [!I. also reduces processing time for determining Eigenfaces
Current Face recognizers can be categorized into two significantly.
goups, component-based face recopizers and image- In the next section we will lntrcduce our face
based face recognizers [?]. Component-based systems use representation system and proposed face recognition
only a few features that are extracted from image. These method. In section 3 the simulation results are reported
features are the important and mostly invariable parts of and comparisons to Eigenface method are made. Finally
face (e.g. eyes, nose, mouth and chin). However, this conclusions are given in section 4.
method has limited applications because of its difficult
implementation and its unreliability in some cases. Image- 2. METHODOLOGY
based systems use a pixel intensity matrix that yields a
high dimensional feature space. The image-based method The first step of every pattern recognition system is
is more desirable for researchers due to its ease of feature extraction. The extracted features must he low in
implementation and robustness. In order to build an dimension and optimum in the discriminatov power
accurate and fast face recognizer, a lower dimension simultaneously in order to decrease the time and error of
representation from the raw image must be obtained. recognition. To achieve these goals a two-stage approach
Principal Components Analysis (PCA), Linear was used for extracting face features. First the mean
Discriminant Analysis (LDA) and Independent image is subtracted from all the training images in order to
Component Analysis (ICA) have been used for this normalize them. A suhband representation of normalized
purpose. Turk successfully used the PCA to represent data was obtained by means of DWT. By applying PCA

0-7803-8554-3/04/$20.00 02004 IEEE. 853

on the suhband images Eigenhces arc obtained (Fig. I). 3.1. DWT-PCA
PCA orthonoimal bases in order to project images into a
lower dimension space for recokmition. These projected Two-dimensional wavelet transform is used in this
vectors are sent to SVM system to train with database method. Thc recognition rate is dependent to the selected
vectors or recognize thc rcccived image identity. wavelet function and the level of decomposition. In order
In our work the various f o m s of wnvelet function are to obtain the hest result, these parameters were examined
used in an attempt to find the optimum one. Thc two- by experiments. Fig. 3 shows emi- rate I‘or difftrent levels
dimensional intensity matrix of the input image w o k s as of decomposition in the training phase. The hest results
the input of DWT system and the output is made by are ohtained when two level of decomposition is used. In
saving thc approximation coefficients and discarding the Fig. 3 and Fig. 5 , DWT-PCA and PCA methods arc
three sets of detail coexffcienls. ‘Thc approximation compared with dilkrcnt orders of polynomial SVM and
coeflicients aic thc input oI‘ thc PCA system to detenninc KBF S V M respectively.
cigcnlaccs (Fig. I ) in the leaming phase or to project
images tu coordinates that are defined hy eigcnfaccs in thc
recognition phase (Fig. 2 ) .

1 le* mMet - REF Sm mfh t e s t Gamma

-.-
-
_b_

2 lejel waxlo(- Pdynmial Sun Order 1

2 iejel wade Pdynmial Sun Older 2
~

-.-
4
-
2 lelel wadet REF h m v i l h k i t Gamma
~

3 lejel ydMd - Pdynmial Sun Order 1

3 leiel rad8 - Pdvnmlal sun order 2

0
Fig 1 Blmk diagram for ohtaining Eigcnfaces by D W - P C A prooess. 50 150 XI)

Fig 3 E m r mte YS. number of Eigenfaces for one (light gray lints), two
(block lines), and three (dark gray lines) levels of DWT decomposition.

Fig 2 Block diagram ofprojecting images into eigcnlvces space.

3. EXPERIMENTAL RESULTS

For evaluating our new method, we have used the

ORL’ database. The ORL face database (developed at the
Olivetti Research Laboratory, Cambridge, U.K.) is
composed of 400 images with ten different images for
each of the 40 distinct subjects. The variations of the
images are across pose, size, time, and facial expression. Fig 4 Error rate VQ. different number of Eigenfacea for PCA method
All the images were taken against a dark homogeneous (gray lines) and DWT-PCAmethod (black lines) using polynomial Svhrl
classitisrs with ditfPrent orders.
background with the subjects in an upright, frontal
position, with tolerance for some tilting and rotation of up
to about 20”. There is mme variation in scale of up to
about 10%. The spatial and grey-level resolutions of the
images are 9’2 112 and 256, respectively. Five images
from each individual are selected randomly for training
and the five rest images are used for testing.

Olivstti Research Laboratory

854
 - m.M , BFSVMGmmail

- PCA-DWT , REF SVM Gmma=O 1

RBF SYM Ganma=O 1

Fig 5 - Emorrole VI. dilkrsnt numbcrot'EigcnCaces for PCA (gray Fig 6 - Enor ralc vs. diffcrcnl numhcr oCEigsnhces for on<_llircc and 5
liner) ;md llic DWT-IC4 mcthods (hlack lincs) using RBF SVhf I w d s ofO\VT dccomporilion (one dimcnsional w v e l r l ) .
clnssilicr with 1uo dift'efcrenl viilues uf(;smma.
3.3. DWT without PCA
With respect to these ligui-cs, it is concludcd that the
ncw method decreases the error ratc by more than 3% In this expcrimcnt, the DWT approximation
relative to thc I'CA method and maintains the property of coefficients arc 1.eordered hy zigzag scanning and the
having the silme or better discriminatoiy power with less SVM inpul wctors are constlucted directly ft-om the
features. A great advantage is that the time of processing rearranged approximation coefiicients. Here face
for determining Eigcdaces decreased sipificantly. This recognition was camicd done without using PCA.
is due to thc fact that wavclet transform reduces the size In Fig. 7 error ratc for three levels of wavelet
of images which must he processed to obtain eigenfaces. decomposition for different number of prescwed
This cffect significantly overcomes the effect of extra approximation coeffcient is shown One can ohtain
time-consuming pmcesing which is done hy wavelct similar mor rate when using a large numher of
transform. coefficients and dimension reduction ability doesn't exist.
The improvement of new DWT-PCA method @y In the case of four level of wavelet decomposition, the
two-dimensional wavelet transform) inspired M to number of coefficients can he rduced significantly but
examine some related methods to discover their effects. error rate is more than the PCA method (Fig. 8).

3.2. D W - P C A Using One-Dimensional Wavelet

Transform

In this experiment one-dimensional wavelet transform

is used instcad of two-dimensional one. The results show
,
that using onc-level of decomposition makes no
4 \
significant changes compared to PCA method. One can
see by increasing levels of decomposition discriminatoiy
power and efficiency reduces extremely (Fig. 6).
This result can he interpreted in this way, the
correlation between each pixel and its' neighbors in the
same row is neglected. In fact this transform supposes
that the image space is a onedimensional space which
reduces between pixels information and consequently the
efficiency. M 60 10 Po 90 rm 110 1 8 ,w 140 If0

Fig 7 Errorrate YS. different number ofcoefficients forthree

level ofDWT deoompasition.

855
 [J] M. A. Turk and A. P. Pentl:ind. "Eigenfaces for.
recognition." Jur~molo/ Cognilive Ne,,roseimce, Vol. 3 .
1991, pp. 71-86
[51 K . Jonsson. J. Matas. J. Kinlerand Y . Li, "Lramingsupport
vectors for facc veriticatian and recognition." Pruc. I E E
bilenrrlior,al Co,&rmce on iluloamlic Foce and Crstrtrc
Rceoprilion, 2000. pp. 208-2 13.
[6] S. 0 Mallnt, "A Thcory lor Multiresolution Signal
Decoiuposition The Wavelct Reprcsentntion."
IEEE.Tro,isoc/iorrs OII Padem .4,mlvsi.~ mid dfachinc
l ~ m l l i ~ e Vol.
m ~ ~II.. 19x9. pp. 674-693.
[7] M . H. Yang, "Kcmcl EigenFaces YS Kcmel Fishcrfaczs:
Face Recognition using Kemcl Methods," Proc. o//lte F$/z
b z l . Cot$ on ~ 4 ~ ~ l o Face~ ~ ~r ~
a d~ Ge.ylwe
l i c Recogrriliorr.
May 2002. pp. 215-220.
[8] V. Vapnik. "Statistical Lcaming T h c o ~ . "John Wilcy &
Sons. New York, 1998.
[9] P. C. Yucln. I).Q.I h i and G.C. Tong, "WnvelGt-boscdPCA
for JUIL:~I facc recognition.''Proc. I
('ullfi.l~<~rrce ion, I!l9X.
ut1 Illloge AllO!l:Fir O l d Ilrll~r.p~'~t
Fig 8 Emor mlc vs. diffemnt numhcr olcorllicicntr for four IWEI pp. 223.228.
of mvr dccvmpoJitim.

3.4. DCT-PCA

Discrete Cosine Transfoim (DCT) is used instead of

DWT in the first stage. l h e results are similar to PCA and
it seems that the DCT has no effect on images. The
representation vectors in two methods (PCA and DCT-
PCA) are also similar in most of coefficients and the few
differences are neglected hy SVM.

4. CONCOLUSIONS
In this paper a new method tor face rcpreszntation and
recognition using DWT and SVM classiIier is proposed.
DWT is used as a preprocessing tool which improves the
recognition performance significantly. This improvement
includes a substantial reduction in mor rate and
processing time of obtaining PCA orthonormal hasis
representation. These improvements lead an enhancement
in efficiency or, in other words, security of system and
moving toward real-time face recognizer. It is noteworthy
that Lhese improvements didn't affect other suitable
properties of PCA method adversely.

5. REFRENCES

R. Chellnppa, C. L. Wilson, and S. Sirohey, "Human and

machine recognition of faces: A survey,'' Proc. IEEE, May
1995,pp. 705-741.
R. Brunelli, and T. Poggio, '"Face recognition: Feahttures
versus templates," IEEE Transaclions on Pallern Anatvsis
andiliadine Iiihlligmce, Vol. 15, n. IO, 1993, pp. 1042-
1052.
C. Cortes, and V. Vapnik, "Support-Vector Nehvorks,"
Machine Learning, Vol. 20, n. 3, Sept. 1995, pp. 273-297.

856