You are on page 1of 18

Beta Wavelet Networks for Face Recognition

Mourad ZAIED, Chokri BEN AMAR and Adel ALIMI

Research Group in Intelligent Machines (REGIM), University of Sfax, B.P. W, 3038, Sfax, Tunisia

Faculty of Science of Sfax, University of Sfax, Tunisia

E-mail: { mourad.Zaied,chokri.benamar, adel.alimi}@ieee.org

Tel: +21674276400

Fax: +21674274437

Abstract: In recent years, an explosion in research on pattern recognition has been observed.

Face recognition is a specialised pattern recognition task with several applications such as security

(access to restricted areas, banking, identity verification, and people recognition at airports).

Face recognition is an example of advanced object recognition. The process is influenced by several

factors such as shape, reflectance, pose, occlusion and illumination which make it even more

difficult. Today there are many well known techniques for face recognition.

In this paper, we present an approach to face recognition based in Beta Wavelet networks. We then

present a series of experimental results for our face recognition system.

Keyword: Image, Beta Wavelet, Wavelet Networks, Face Recognition

Introduction:

The Wavelet networks (WNs) theory was introduced in 1992 by Zhang and Benveniste as a

combination of artificial neural radial basis function (RBF) networks and wavelet decomposition.

Since then they have received little attention in recent publications except some searchers who have

used WNs for signal representation and classification. They have explained how a WN can be

-1-
generated and showed how they can be used for pattern matching. In addition, they mention the

large data compression achieved by such a WN representation. Zhang showed that WNs are able to

handle nonlinear regression of moderately large input dimension with sparse training data. Recently

some researchers like kruger and Feris have used WNs to trace and recognize an object using a 2D

Gabor Wavelet Networks.

A - From the Fourier analysis to wavelets

To get temporal and frequency information of a signal x(t) , it is necessary to decompose it on

functions localized both in time and in frequency. To define these functions, it is necessary to begin

from a function ψ (t ) named ''mother wavelet'' well localized and oscillating (it looks like a wave,

but being localized). The condition of localization is written as the usual shape of decrease in fast

amplitude when t increases indefinitely. The condition of oscillation suggests that ψ (t ) vibrates like

a wave: we also ask that the integral of ψ()


t is equal to zero.

The mother wavelet generates the others wavelets of the family: ψ a,b (t) a>0 and b real, by scaling

(variation of the a parameter) and by shifting in the time (variation of the b parameter).

1 t −b
ψ a,b (t ) = ψ( ) (1)
a a

For the waveletψ a,b , b intervenes in the shifting of the mother wavelet and a in its scaling. This

wavelet is localized in time on the interval [b, b+L*a], if the mother wavelet is localized on [0 , L],

and in frequency on the interval [f0/a , f1/a], if the mother wavelet is localized on [f0 , f1].

According to this definition, we can imagine easily that the high wavelets correspond to a<1

(narrow windows) and the low wavelets correspond to a>1 (large windows).

-2-
Grossman and Morlet showed that when ψ (t ) is a real value this collection can be used as an

orthonormal basis. This means that every finished signal of energy can be written as a linear

combination of waveletsψ a,b (t) and that the coefficients of this combination are the scalar products:

+∞
1 t −b
C ( a, b ) = ∫
a −∞
x(t )ψ (
a
) (2)

warehouse are rarely static, and they have a complex life cycle.

Properties of a mother wavelet [17]

The most important properties of a wavelet are:

1) Admissibility

Let’s consider a function ψ belonging to L2(R) and TF (ψ ) is its Fourier transform. ψ is called

mother wavelet if it satisfies the following condition of admissibility:

+∞ TF (ψ (ω )) 2
∫ dω < +∞ (3)
−∞ ω

2) Localization

A wavelet is a function that must have fast decrease on the two sides of its domain of definition or

better it must have a compact support (null outside of a finished interval).

-3-
3) Oscillation (Moment of order 0)

The wavelet must verify

∫ψ(t)dt =0 (4)

ψ (t ) should have an undulatory character, it changes sign at least once.

4) Shifting and scaling

The mother wavelet must satisfy the properties of Shifting and scaling for what can generate other

wavelets.

B- Continuous Wavelet Transform

A wavelet expansion consists in scaling and shifting of only one and same fixed function: the

waveletψ ∈ L2 (ℜ) .

In continuous wavelet transform, the parameters of scaling and shifting vary continuously which

means that we use the functions:

1 t −b
ψ a,b (t) = ψ( ) with a, b ∈ℜ, a ≠ 0 (5)
a a

The continuous wavelet transform of a function f is defined by:

w(a, b) =< f ,ψ > (6)


ab

If the wavelet is admissible, the continuous wavelet transform admits an inverse f(x) as:

-4-
+∞ +∞ w(a, b)ψ ( x − b ) dadb
f ( x) = ∫−∞ (7)
∫−∞
a

C- Introduction to Wavelet Networks

From the inverse wavelet transform to the Wavelet Networks

The equation (7) gives the expression of an f function with 2 integrations on all possible dilatations

and all possible shifts of the mother wavelet. Suppose that we dispose only a finite number N of

wavelets. We can consider the relation:

N
f ( x) ≈ ∑ wiψ i (8)
i =1

As an approximation of the relation (7). The finite sum of the relation (8) is an approximation of the

inverse transform. We can view it also as a decomposition of the function f to a sum of coefficients

wi and waveletsψ .
i

To define a WN, we begin by taking a family of N wavelet functions Ψ = {ψn1,...,ψnN } with

parameter vectors n =(a,b )T of some mother wavelet ψ.

The b defines the scaling parameter of the wavelet and the a defines the shifting parameter. Those

parameters may be chosen arbitrarily at this point. According to wavelet theory, any function f

belonging to L2(R) space can be loosely represented by their continuous wavelet transform and

thus, with arbitrary precision, by a wavelet network.

The wavelet Network is defined graphically as:

-5-
ψ
w1
x1 ψ w2
∑ yi

....
x2
.
ψ wj
.

....
xd
ψ

Figure 1. Wavelet Network

In order to find the WN for the function f we minimize, using the LevenbergMarquardt method, the

energy functional:

N
E = min f − ∑ wiψ n (9)
wi ni i =1 i

With respect to the weights wi and the wavelet parameter vectors ni, Equation (8) states that the wi

and ni are optimized, this means that the translation and the dilation of each wavelet are chosen such

so the image is optimally approximated by the weighted sum of wavelets ψni. We therefore define a

wavelet network as follows:

• Definition: Let ψni i=1,...,N be a set of wavelets, f a function and wi and ni chosen

according to the energy functional (9). The vector Ψ =(ψ1,...,ψN )T and the matrix w

=(w11,...,wnn ) define then the wavelet network (Ψ,w) for the function f.

-6-
D- Face Recognition by Beta wavelet networks

The rest of this paper will be reserved for the usage of the Beta wavelet networks for face

recognition. This survey will be made through the use of the Beta wavelets to construct a wavelet

networks.

Definition and Basic Properties of the Beta Wavelet

The Beta function is defined by:

⎧⎛ p q
⎪⎜ x− x0 ⎞⎟ ⎛⎜ x − x ⎞⎟
⎪ 1 si x∈]x ,x [
β(x;p,q, x , x ) = ⎨⎜⎜ x − x ⎟⎟ ⎜⎜ x − x ⎟⎟ 0 1
0 1
⎪⎝ c 0 ⎠ ⎝ 1 c ⎠
⎪ 0 otherwise
(10)

px + qx
with p,q, x < x ∈ℜ and x = 1 0
0 1 c p+ q

The Beta function possesses the following properties:

β ( x0 ) = β ( x1 ) = 0
(11)
β ( xc ) = 1

d β ( x ) px1 + qx0 − ( p + q ) x
= β ( x)
dx ( x − x )( x − x )
0 1 (12)
d β ( xc ) d β ( x0 ) d β ( x1 )
= = =0
dx dx dx

p xc − x0
= (13)
q x − xc
1

-7-
d 2 β ( x)
= β ( x) A( x) (14)
dx

1 ⎡ 1 1 ⎤
A(x) = ⎢ − −(p+q)(x+1)+ px + px ⎥ (15)
(x−x )(x −x) ⎢(x −x) (x−x ) 1 0
0 1 ⎣ 1 0 ⎦⎥

We demonstrate in [15] [16] [17] [18] that all the derivatives of the Beta function are wavelets.

We can get different wavelets when we modify the values of the q and p parameters.

Figure : Beta 1 Wavelet (First derivative of the Beta Function) and Beta 2 Wavelet (Second derivative of the Beta Function)

Our approach for face recognition

1) Training

The goal was to recognize a face independing of its expression. We proceeded as follows: a WN

(Ψ,w) was optimized for each training face which resulted in a set of template WNs, We chose the

faces with the “normal” expressions to be our gallery faces. For all the training faces we calculate

-8-
the mean square error (MSE) between the original image and the approximated by the network then

we save the wavelet network parameters and the corresponding MSE.

1 N M 2
MSE = ∑ ∑ ( A ( i, j ) − B ( i, j ) ) (16)
M * N i =1 j =1

M and N : Image dimensions

A : Input Image B : Output Image

x1 w11 y1
a1

b1
w1j
xj yj

w1m
bk
ak
xm ym
ai
bi
ai: Wavelet scaling parameters wi
bi : Wavelet shifting MSE

parameters
wi: Network connections weight
Base of parameters
(a network / person)

Figure 2 : Training process of a face image

2) Recognition

To recognize a face, we approximate it by the networks then we also calculate the MSE for it. Now

we compare this error to the existing in the base to find the nearest that is generally for the searched

face. The system does not know the face if the error is not near to all the errors of training faces. We

say that an error is not near if its distance passes a fixed threshold.

-9-
Figure 3: Person identified by the system

Figure 4: Person not identified by the system

E- Experimental Results

In this section we will present the results of a face recognition experiment, using the ORL face

database AT&T Laboratories Cambridge and the YALE face database.

The ORL face database contains 40 persons with 10 images per person.

- 10 -
Figure 5:The set of image for one subject of ORL database

Figure 6:The 40 subject of the ORL face

The YALE face database has 15 persons with 11 images per person. The individuals show different

facial expressions on all of their images (happy, sad, surprised, etc.).

- 11 -
Figure 7:The set of image for one subject of Yale database

• First evaluation:

To evaluate our system we calculate the rate of the correct recognitions on a base with 2

persons, we increase after that the number of persons until we evaluate the entire base. We use the

Beta 2 Wavelet with the p and q parameters equal to 25.

- 12 -
With the ORL Base:

Number of persons Correct recognitions False recognitions Rate

2 20 0 1,000
3 30 0 1,000
4 37 3 0,925
5 45 5 0,900
6 55 5 0,917
7 65 5 0,929
8 75 5 0,938
9 83 7 0,922
10 90 10 0,900
20 168 34 0,832
25 206 44 0,824
30 245 55 0,817
40 365 75 0,830
Table 1: Rate of recognition of ORL faces

Recognition rate (ORL Base)


100%
95%
90%
85%
Rate

80%
75%
70%
65%
60%
2 3 4 5 6 7 8 9 10 20 25 30 40
Nbr of Personnes/base
Recognition rate

Figure 8: Recognition rate of ORL database

- 13 -
With the Yale Base:

Number of persons Correct recognitions False recognitions Rate

2 20 0 1,000
3 29 1 0,970
4 37 3 0,932
5 45 5 0,909
6 54 6 0,909
7 63 7 0,909
8 71 9 0,898
9 76 14 0,859
10 68 18 0,813
11 83 27 0,777
12 90 30 0,773
13 99 31 0,783
14 107 33 0,786
15 113 37 0,776
Table 2: Rate of recognition of YALE faces

Recognition rate (YALE Base)

100%

90%
Rate

80%

70%

60%
2 3 4 5 6 7 8 9 10 11 12 13 14 15
Nbr of Personnes/base

Recognition rate

Figure 9: Recognition rate of Yale database

- 14 -
• Second evaluation:

To know the minimum number of wavelets necessary to get the maximum number of correct

recognition we use wavelet networks with different number of wavelets.

Nombre of Wavelets Correct recognitions false recognitions Rate

1 62 10 0,875
2 65 8 0,901
3 66 6 0,925
4 67 5 0,938
10 67 5 0,938
15 67 5 0,938
Table 3: Rate of recognition of ORL faces of 8 persons with different numbers of Wavelets

Recognition rate

100%

95%
Rate

90%

85%

80%
2 3 4 5 6 7
Wavelets number
Recognition rate

Figure 10: Rate of recognition of ORL faces of 8 persons with different numbers of Wavelets

- 15 -
CONCLUSIONS AND FUTURE WORK

In conclusion, a system capable of performing the task of face recognition has been designed. It is

based on a hierarchical wavelet network. Our method consists on two parts: the first is to train

networks on a set of faces images to have a wavelet networks per person, the second is to test it on

faces images of people belonging to the training base or not.

The performance of the Beta Wavelet networks as a classifier suitable for face recognition is

evident through the results.

To give an increase of performance, all systems with recognition rates in excess of 90% use a

feature extraction stage. It is still believed that with a correct implementation of the feature

extraction stage that the Beta Wavelet networks classifier recognition rate would be in the range of

90 to 95 percent.

- 16 -
REFERENCES

[1] Q. Zhang and A. Benveniste. Wavelet networks. IEEE Trans. Neural Networks, 3:889–898,

1992.

[2] H. Szu, B. Telfer, and S. Kadambe. Neural network adaptive wavelets for signal representation

and classification. Optical Engineering, 31:1907–1961, 1992.

[3] H. Szu, B. Telfer, and J. Garcia. Wavelet transforms and neural networks for compression and

recognition.

[4] Q. Zhang. Using wavelet network in nonparametric estimation. IEEE Trans. Neural Networks,

8(2):227– 236, 1997.

[5] C. C. Holmes and B. K. Mallick. Bayesian wavelet networks for nonparametric regression.

IEEE Trans. Neural Networks, 11:27–35, 2000.

[6] L. Reyneri. Unification of neural and wavelet networks and fuzzy fystems. IEEE Trans. Neural

Networks, 10:801–814, 1999.

[7] Daubechies. The wavelet transform, time frequency localization and signal analysis. IEEE

Trans. Information Theory, 36:961–1005, 1990.

[8] R. Feris, V. Krüger, and R. Cesar Jr. Efficient real-time face tracking in wavelet subspace. In

Proceedings of the Int. Workshop on Recognition, Analysis and Tracking of Faces and Gestures

in Real-Time Systems, pages 113–118, Vancouver, BC, Canada, 2001, in conjunction with the

ICCV’01, 2001. IEEE Computer Society.

[9] V. Kruger and G. Sommer. Affine real-time face tracking using gabor wavelet networks. In

Proc. Int.Conf. on Pattern Recognition, Barcelona, Spain, Sept. 3-8, 2000. IEEE Computer

Society.

- 17 -
[10] A. Pentland. Looking at people: sensing for ubiquitous and sensable computing. IEEE

Trans. Pattern Analysis and Machine Intelligence, 22:107–119, 2000.

[11] V. Kruger, S. Bruns, and G. Sommer. Efficient head pose estimation with gabor wavelet

networks. In Proc. British Machine Vision Conference, Bristol, UK, Sept. 12-14, 2000. BMVC.

[12] J. Bruske and G. Sommer. Dynamic cell structure learns perfectly topology preserving map.

Neural Computation, 7:845–865, 1995.

[13] H. Ritter, T. Martinez, and K. Schulten. Neuronale Netze. Addison-Wesley, 1991.

[14] V. Krüger. Gabor wavelet networks for object representation. Technical Report CS-TR-

4245, University of Maryland, CFAR, May 2001.

[15] Chokri BEN AMAR, Mourad ZAIED and Adel ALIMI, Beta Wavelets Synthesis and

application to lossless Image Compression. Advanced in engineering software

[16] Zaied M., Ben Amar C. and Alimi M.A. "Award a New Wavelet Based Beta Function",

International Conference on Signal, System and Design, SSD03, Tunisia, Mars, 2003, vol. 1, P.

185-191.

[17] Bellil W., Ben Amar C. et Alimi M.A. "Beta Wavelet Based Image Compression",

International Conference on Signal, System and Design, SSD03, Tunisia, Mars, 2003, vol. 1,

pp. 77-82.

[18] Bellil W., Ben Amar C., Zaied M. and Alimi M.A. "La fonction Bêta et ses dérivées : vers

une nouvelle famille d’ondelettes", First International Conference on Signal, System and

Design, SCS’04, Tunisia, Mars, vol. 1, P. 201-207.

- 18 -

You might also like