Professional Documents
Culture Documents
Neural Network
Huiwen Deng*(Corresponding
author)
TangquanQi
School of Computer and Information Science
Southwest China University
Chongqing, China
e-mail: qtq2002@swu.edu.cn
has
experiment
been
results
tested
show
on
that
the
algorithm
reduces
the
of
human
face.
And
by
optimizing
the
recognition;
eigenfaces;
fisher
linear
I.
Weiping Hu
Institute of Logic and Intelligence
Southwest China University
Chongqing, China
e-mail: huwp2000@163.com
INTRODUCTION
166
"I
i=1
(3)
1=1
vlk<l>k,
1, ,3,..., M
=[
Sb
i=l
i
n ui - li ui
li
(5)
(6)
Where
1
ui'
= -L
M
M i=l
= 1,2,3,.
..
, M
is the
mean of
is the mean
= t =
of i th set of eigenface. c is the number of the class and ni
i=l
"i ,
1,2,3,... ,
R(Sb)=c-l
R(Sw)=n-c
(7)
W'=argmawx
T
w S w
I
IW
Sww
= [W1'"'2,W3"'"
i
l
(9)
We-I]
(1)
lPi=Fi-'I'
i=1
'1':
i=1,2,... ,M
and
Sw:
Sb = :t {
1
'I'=Lri
M i=l
RECOGNITION APPROACH
= 1 L<P<P =AA
Fi
i
Pij(xi)= exp - (x :
167
(10)
lfJ j
exp
i=1
TABLE I.
(j2
)
(11)
C j = ( cl
center of thej th RBF unit. From Eq. (11), we can see that
each node in this layer also represents an RBF unit. In the
sequel, RBF nodes are always used to represent rules
without interpretation.
Layer 4 We call these nodes as N nodes. Obviously, the
number of N nodes is equal to that of R nodes. The output
ofis
If! j -
fP j
-u -'
L fPk
1,2,
...
, u
(12)
Figure 1.
architecture of DFNN
k=1
y(X)=fWk'l'k
k=l
(13)
where k =1,2,...,u. .
C.
output
Algorithm Architecture
L----N-------<
Y--.output
168
Figure 4.
TABLE II.
Parameter
Min
max
type
'1'
10304*1
50.1800
184.1000
double
80*100
-4.2754e+06
3.683e+06
double
w"
19*100
- 1.7 105
1.9336
double
V_FLD
80* 19
-4.0423e+07
6.344Ie+07
double
(b)
(a)
Figure 5.
(a) the mean of all training face images, (b) the output matrix of
w*.
i:O
Experiment Results
.1
property
Value
EXPERIMENT
"
... .
.
..
111
III
Il
..
.
.
Figure 6. (a) the actual output error, (b) the fuzzy rule generation, (c)the
root mean squared error (RMSE), (d) the desired actual output and the input
data
169
TABLE III.
The
number
of
Eave
/%
simulation
D.
1.92
M-PCA[18]
10
2.4
PCA+ RBF[9]
4.9
Wavelet + RBF[IO]
3.7
CNN[ll]
3.83
EFLD+ DFNN
1.80
IV.
niS
[5]
A.M. Martinez, A.C. Kak. "PCA versus LDA," IEEE Trans, Pattern
Anal. Machine Intell, vo1.23, no.2, 2001, pp.228-233.
[6]
[7]
[8]
[9 ]
ACKNOWLEDGMENT
This paper is supported by the Key Project of
Chongqing(project no. 08jwsk277).
REFERENCES
X.Y. Jing, Y.F. Yao, lY. Yang, David Zhang. "A novel face
recognition approach based on kernel discriminative common vectors
[4]
[2]
CONCLUSION
[3]
...!.i=l,--_
tot
[I]
network,"
(15)
qn
Where, q represents the number of experiments, and
i
n rniS is the number of wrong classification in the ith epoch.
And qntot represents the total number of testing sample.
Based on Eave rule, the result of comparison of the
perfonnance in the same ORL face database is shown in
Table III. In this paper, the EFLD + DFNN algorithm Eave is
2.42.
Eave =
neural
170