Open Access proceedings Journal of Physics: Conference series



Download 0,7 Mb.
Pdf ko'rish
bet5/7
Sana27.01.2022
Hajmi0,7 Mb.
#412980
1   2   3   4   5   6   7
k
k
k
k
+
=

where 
)
(
H
k
observation matrix
)
(
w
k
– noise affecting the reference points of the image 
outline. 
The linear filtering mechanism is implemented as a Kalman filter [11] 
)
(
F
)
(
D
)
(
)
(
B
)
1
(
x
)
(
Φ
)
1
|
(
x
0
0
k
k
k
U
k
k
k
k
k
+
+

=


( )
( ) (
)
{
}



+

=
=
N
i
i
i
k
k
k
H
k
z
k
K
k
k
k
1
0
0
0
1
|
x
)
(
)
1
|
(
x
)
(
x

( )
( ) (
)
( ) (
) ( )
[ ]
{
}
1
V
H
1
|
P
H
H
1
|
K

+


=
k
k
k
k
k
k
k
P
k
S
k
vi
T
T
i
i

(
)
( ) ( ) ( )
( ) (
) ( )
k
k
P
k
k
k
V
k
k
k
T
T
w
Ф
1
Ф
G
G
1
|
P

+
=




AMSD 2020
Journal of Physics: Conference Series
1791
(2021) 012099
IOP Publishing
doi:10.1088/1742-6596/1791/1/012099
3
(
)
( ) (
)

=



=
=
N
i
i
N
i
k
k
k
k
k
k
k
1
,...,
1
,
1
|
P
H
)
(
K
1
|
P
)
(
P

where 
( )
k
z
i
– vector of observations; 
( ) (
)
1
|
x
H
0
0

=
n
n
n
z
– vector of estimates of observations; 
( )
n
0
x
– estimate the state vector
(
)
1
|
x
0

k
k
– estimate the state lead vector; 
( )
k
Φ
– transition matrix; 
( )
k
H
– observation matrix; 
( )
k
i
K
– coefficient matrix; 
(
)
1
|
P

k
k
– dispersion matrix of a state vector; 
( )
k
P
– dispersion matrix of the state vector; 
( )
k
U
– control vector; 
( )
k
F
– vector of measured signals 
from the object output; 
( )
k
B
– matrix of control coefficients; 
( )
k
D
matrix of measurement 
coefficients; 
( )
k
S
i
– meter sign; 
( )
0
=
k
S
i
.
The lead value of the contour point is specified as 
( ) ( ) ( ) ( )
1
-

Ф
C
ˆ
k
k
k
k
y
=

The difference between the anticipated and actually observed points is set as
( ) ( ) ( )
k
k
k
e

y

=

The Kalman filter gain is defined as
( ) (
) ( ) ( ) (
) ( )
( )
(
)
1
Q
C
1
P
C
C
1
P
K

+

×

=
k
k
k
k
k
k
k
M
T
T

The proposed image filtering mechanisms for solving 
smoothing problems are considered in three-
dimensional space and implemented on the basis of the 
cyclic multigrid method in a parallel computing 
environment. The study was carried out according to 
the coefficient of gain in filtration, the values of which 
are determined as the ratio 
σ
σ
/
p
, where 
p
σ
– the 
filtering error on 
σ
– the variance of the input process.
In figure 1. shows graphs of the gain in filtering 
depending on the values of the parameter 
B
P
G
σ
=

where 
P
– the probability of relaxation of the reference 
points of the image contour due to noise; 
B
– the range 
of change in the coordinates of reference points on the 
plane, usually specified by 
10
=
B
. Charts 1- strategies of rule 
σ
3
±
are illustrated; 2 - threshold 
adaptive control; 3 – linear Kalman filter. Graphs are obtained with 
3
10

=
P
values; 
( )
.
10
;
7
.
0
;
05
.
0
=
=
=
B
R
τ
σ
The efficiency of the mechanism is increased by using a differential operator based on adjusting the 
orders of the approximation model depending on the mesh size. A constructive approach is proposed, 
aimed at the recognition and classification of micro-objects with implementations of computational 
schemes of a three-layer neural network (NN), learning algorithms, and retranslation of the process 
dynamics to an image identification optimization model under conditions of nonstationarity and 
parametric uncertainty.
Mechanisms for searching for correlations, tendencies, relationships, patterns in the dynamics of 
images have been used and implemented. Tools for interpreting dependencies, using templates, and 
regulating variables have been obtained.
2.2.
 
Mechanisms for adaptive identification of micro-objects of various dimensions 
The solution to the problem of identifying micro-objects is based on scaling tools, selection of 
reference points of the contour, threshold control, reduction of zero points, calculation of the root-
mean-square error from the corresponding functions of the input and reference images. Many micro-
objects have different dimensions, which negatively affect the quality of image identification and the 
loss of useful information occurs, therefore, it is necessary to study the effect of the operation of 
reducing the size of digital images to a certain threshold. A technique has been developed, 
mechanisms obtained by which do not depend on the size of the image. And it is aimed only at finding 
the required function by its integrals in the family of lines on the basis of the Mellin transformation.

Download 0,7 Mb.

Do'stlaringiz bilan baham:
1   2   3   4   5   6   7




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©hozir.org 2024
ma'muriyatiga murojaat qiling

kiriting | ro'yxatdan o'tish
    Bosh sahifa
юртда тантана
Боғда битган
Бугун юртда
Эшитганлар жилманглар
Эшитмадим деманглар
битган бодомлар
Yangiariq tumani
qitish marakazi
Raqamli texnologiyalar
ilishida muhokamadan
tasdiqqa tavsiya
tavsiya etilgan
iqtisodiyot kafedrasi
steiermarkischen landesregierung
asarlaringizni yuboring
o'zingizning asarlaringizni
Iltimos faqat
faqat o'zingizning
steierm rkischen
landesregierung fachabteilung
rkischen landesregierung
hamshira loyihasi
loyihasi mavsum
faolyatining oqibatlari
asosiy adabiyotlar
fakulteti ahborot
ahborot havfsizligi
havfsizligi kafedrasi
fanidan bo’yicha
fakulteti iqtisodiyot
boshqaruv fakulteti
chiqarishda boshqaruv
ishlab chiqarishda
iqtisodiyot fakultet
multiservis tarmoqlari
fanidan asosiy
Uzbek fanidan
mavzulari potok
asosidagi multiservis
'aliyyil a'ziym
billahil 'aliyyil
illaa billahil
quvvata illaa
falah' deganida
Kompyuter savodxonligi
bo’yicha mustaqil
'alal falah'
Hayya 'alal
'alas soloh
Hayya 'alas
mavsum boyicha


yuklab olish